@pathmode/mcp-server 1.2.2 β†’ 1.3.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (5) hide show
  1. package/README.md +188 -104
  2. package/dist/api-client.d.ts +102 -0
  3. package/dist/api-client.d.ts.map +1 -1
  4. package/dist/index.js +237 -2
  5. package/package.json +1 -1
package/README.md CHANGED
@@ -1,153 +1,237 @@
1
- # MCP Registry
1
+ # @pathmode/mcp-server
2
2
 
3
- The MCP registry provides MCP clients with a list of MCP servers, like an app store for MCP servers.
3
+ Build structured intent specs through Socratic AI conversation β€” right in your terminal.
4
4
 
5
- [**πŸ“€ Publish my MCP server**](docs/modelcontextprotocol-io/quickstart.mdx) | [**⚑️ Live API docs**](https://registry.modelcontextprotocol.io/docs) | [**πŸ‘€ Ecosystem vision**](docs/design/ecosystem-vision.md) | πŸ“– **[Full documentation](./docs)**
5
+ No signup. No API key. Just add the MCP server and start talking.
6
6
 
7
- ## Development Status
7
+ ## Intent Compiler
8
8
 
9
- **2025-10-24 update**: The Registry API has entered an **API freeze (v0.1)** πŸŽ‰. For the next month or more, the API will remain stable with no breaking changes, allowing integrators to confidently implement support. This freeze applies to v0.1 while development continues on v0. We'll use this period to validate the API in real-world integrations and gather feedback to shape v1 for general availability. Thank you to everyone for your contributions and patienceβ€”your involvement has been key to getting us here!
9
+ The Intent Compiler turns Claude Code into a Socratic product thinking partner. Describe a problem, paste a support ticket, or explain what's broken β€” Claude challenges vague thinking, asks pointed questions, and builds a structured spec.
10
10
 
11
- **2025-09-08 update**: The registry has launched in preview πŸŽ‰ ([announcement blog post](https://blog.modelcontextprotocol.io/posts/2025-09-08-mcp-registry-preview/)). While the system is now more stable, this is still a preview release and breaking changes or data resets may occur. A general availability (GA) release will follow later. We'd love your feedback in [GitHub discussions](https://github.com/modelcontextprotocol/registry/discussions/new?category=ideas) or in the [#registry-dev Discord](https://discord.com/channels/1358869848138059966/1369487942862504016) ([joining details here](https://modelcontextprotocol.io/community/communication)).
11
+ ```
12
+ > Help me write an intent spec for our checkout flow
12
13
 
13
- Current key maintainers:
14
- - **Adam Jones** (Anthropic) [@domdomegg](https://github.com/domdomegg)
15
- - **Tadas Antanavicius** (PulseMCP) [@tadasant](https://github.com/tadasant)
16
- - **Toby Padilla** (GitHub) [@toby](https://github.com/toby)
17
- - **Radoslav (Rado) Dimitrov** (Stacklok) [@rdimitrov](https://github.com/rdimitrov)
14
+ What's broken about it? When you say "checkout flow" β€” is the whole
15
+ thing failing, or is there one specific moment where users bail?
18
16
 
19
- ## Contributing
17
+ > Payment step times out and users get confused
20
18
 
21
- We use multiple channels for collaboration - see [modelcontextprotocol.io/community/communication](https://modelcontextprotocol.io/community/communication).
19
+ When you say "times out" β€” is that 5 seconds or 30? And what does
20
+ the user actually see? A spinner? A blank screen? An error?
22
21
 
23
- Often (but not always) ideas flow through this pipeline:
22
+ > About 8 seconds, they see a spinner with no feedback
24
23
 
25
- - **[Discord](https://modelcontextprotocol.io/community/communication)** - Real-time community discussions
26
- - **[Discussions](https://github.com/modelcontextprotocol/registry/discussions)** - Propose and discuss product/technical requirements
27
- - **[Issues](https://github.com/modelcontextprotocol/registry/issues)** - Track well-scoped technical work
28
- - **[Pull Requests](https://github.com/modelcontextprotocol/registry/pulls)** - Contribute work towards issues
24
+ Proposed Objective: "Reduce cart abandonment caused by payment step
25
+ timeouts exceeding 3 seconds, where users see a spinner with no
26
+ status feedback or recovery path."
29
27
 
30
- ### Quick start:
28
+ Does that capture it, or is there more to the pain?
29
+ ```
31
30
 
32
- #### Pre-requisites
31
+ When the spec is ready, Claude saves it as `intent.md` and optionally exports as `.cursorrules` or `CLAUDE.md` β€” so every AI agent in your project sees the intent as its implementation context.
33
32
 
34
- - **Docker**
35
- - **Go 1.24.x**
36
- - **ko** - Container image builder for Go ([installation instructions](https://ko.build/install/))
37
- - **golangci-lint v2.4.0**
33
+ ### Quick Start
38
34
 
39
- #### Running the server
35
+ Add to `.claude/settings.json`:
40
36
 
41
- ```bash
42
- # Start full development environment
43
- make dev-compose
37
+ ```json
38
+ {
39
+ "mcpServers": {
40
+ "pathmode": {
41
+ "command": "npx",
42
+ "args": ["@pathmode/mcp-server"]
43
+ }
44
+ }
45
+ }
44
46
  ```
45
47
 
46
- This starts the registry at [`localhost:8080`](http://localhost:8080) with PostgreSQL. The database uses ephemeral storage and is reset each time you restart the containers, ensuring a clean state for development and testing.
48
+ Then in Claude Code:
47
49
 
48
- **Note:** The registry uses [ko](https://ko.build) to build container images. The `make dev-compose` command automatically builds the registry image with ko and loads it into your local Docker daemon before starting the services.
49
-
50
- By default, the registry seeds from the production API with a filtered subset of servers (to keep startup fast). This ensures your local environment mirrors production behavior and all seed data passes validation. For offline development you can seed from a file without validation with `MCP_REGISTRY_SEED_FROM=data/seed.json MCP_REGISTRY_ENABLE_REGISTRY_VALIDATION=false make dev-compose`.
50
+ ```
51
+ > Help me write an intent spec for [your problem here]
52
+ ```
51
53
 
52
- The setup can be configured with environment variables in [docker-compose.yml](./docker-compose.yml) - see [.env.example](./.env.example) for a reference.
54
+ That's it. No API key needed.
53
55
 
54
- <details>
55
- <summary>Alternative: Running a pre-built Docker image</summary>
56
+ ### What You Get
56
57
 
57
- Pre-built Docker images are automatically published to GitHub Container Registry:
58
+ **intent.md** β€” Structured spec with YAML frontmatter:
59
+ ```markdown
60
+ ---
61
+ id: "intent_17291..."
62
+ version: 1
63
+ status: "draft"
64
+ ---
65
+ # Fix Checkout Payment Timeout
58
66
 
59
- ```bash
60
- # Run latest stable release
61
- docker run -p 8080:8080 ghcr.io/modelcontextprotocol/registry:latest
67
+ ## Objective
68
+ Reduce cart abandonment caused by payment step
69
+ timeouts exceeding 3 seconds.
62
70
 
63
- # Run latest from main branch (continuous deployment)
64
- docker run -p 8080:8080 ghcr.io/modelcontextprotocol/registry:main
71
+ ## Outcomes
72
+ - [ ] Payment completes in under 3 seconds (p95)
73
+ - [ ] Users see real-time status during processing
74
+ - [ ] Failed payments show actionable error with retry
65
75
 
66
- # Run specific release version
67
- docker run -p 8080:8080 ghcr.io/modelcontextprotocol/registry:v1.0.0
76
+ ## Edge Cases
77
+ - **Network timeout during payment**: Show retry button, no double-charge
78
+ - **Unknown provider status**: Hold order, notify user within 30s
79
+ ```
68
80
 
69
- # Run development build from main branch
70
- docker run -p 8080:8080 ghcr.io/modelcontextprotocol/registry:main-20250906-abc123d
81
+ **.cursorrules** β€” Agent-directive format for Cursor:
82
+ ```
83
+ # CURRENT OBJECTIVE
84
+ You are implementing: "Fix Checkout Payment Timeout"
85
+
86
+ # SUCCESS OUTCOMES
87
+ Your implementation MUST satisfy ALL of these:
88
+ - Payment completes in under 3 seconds (p95)
89
+ - Users see real-time status during processing
90
+ - Failed payments show actionable error with retry
71
91
  ```
72
92
 
73
- **Available tags:**
74
- - **Releases**: `latest`, `v1.0.0`, `v1.1.0`, etc.
75
- - **Continuous**: `main` (latest main branch build)
76
- - **Development**: `main-<date>-<sha>` (specific commit builds)
93
+ **CLAUDE.md** β€” Appends a `<!-- PATHMODE:START -->` section so Claude Code sees the intent in every conversation.
77
94
 
78
- </details>
95
+ ### Intent Compiler Tools
79
96
 
80
- #### Publishing a server
97
+ | Tool | Description |
98
+ |------|-------------|
99
+ | `intent_save` | Save an intent spec to `intent.md` in the project root |
100
+ | `intent_export` | Export as `.cursorrules` or `CLAUDE.md` section |
81
101
 
82
- To publish a server, we've built a simple CLI. You can use it with:
102
+ ### Intent Compiler Prompt
83
103
 
84
- ```bash
85
- # Build the latest CLI
86
- make publisher
104
+ | Prompt | Description |
105
+ |--------|-------------|
106
+ | `compile-intent` | Start a Socratic conversation to build an intent spec |
87
107
 
88
- # Use it!
89
- ./bin/mcp-publisher --help
90
- ```
108
+ ---
91
109
 
92
- See [the publisher guide](./docs/modelcontextprotocol-io/quickstart.mdx) for more details.
110
+ ## Team Features (API Key Required)
93
111
 
94
- #### Other commands
112
+ For teams shipping with AI agents, connect to your [Pathmode](https://pathmode.io) workspace for dependency tracking, strategic context, and governance.
95
113
 
96
- ```bash
97
- # Run lint, unit tests and integration tests
98
- make check
114
+ ### Setup with API Key
115
+
116
+ ```json
117
+ {
118
+ "mcpServers": {
119
+ "pathmode": {
120
+ "command": "npx",
121
+ "args": ["@pathmode/mcp-server"],
122
+ "env": {
123
+ "PATHMODE_API_KEY": "pm_live_..."
124
+ }
125
+ }
126
+ }
127
+ }
99
128
  ```
100
129
 
101
- There are also a few more helpful commands for development. Run `make help` to learn more, or look in [Makefile](./Makefile).
130
+ Works with Claude Code (`.claude/settings.json`), Claude Desktop (`claude_desktop_config.json`), and Cursor (`.cursor/mcp.json`).
102
131
 
103
- <!--
104
- For Claude and other AI tools: Always prefer make targets over custom commands where possible.
105
- -->
132
+ Get your API key from **Settings > API Keys** in the [Pathmode app](https://pathmode.io).
106
133
 
107
- ## Architecture
134
+ ### Local Mode (Offline)
108
135
 
109
- ### Project Structure
136
+ Read `intent.md` files from your project directory without an API key:
110
137
 
138
+ ```json
139
+ {
140
+ "mcpServers": {
141
+ "pathmode": {
142
+ "command": "npx",
143
+ "args": ["@pathmode/mcp-server", "--local"]
144
+ }
145
+ }
146
+ }
111
147
  ```
112
- β”œβ”€β”€ cmd/ # Application entry points
113
- β”‚ └── publisher/ # Server publishing tool
114
- β”œβ”€β”€ data/ # Seed data
115
- β”œβ”€β”€ deploy/ # Deployment configuration (Pulumi)
116
- β”œβ”€β”€ docs/ # Documentation
117
- β”œβ”€β”€ internal/ # Private application code
118
- β”‚ β”œβ”€β”€ api/ # HTTP handlers and routing
119
- β”‚ β”œβ”€β”€ auth/ # Authentication (GitHub OAuth, JWT, namespace blocking)
120
- β”‚ β”œβ”€β”€ config/ # Configuration management
121
- β”‚ β”œβ”€β”€ database/ # Data persistence (PostgreSQL)
122
- β”‚ β”œβ”€β”€ service/ # Business logic
123
- β”‚ β”œβ”€β”€ telemetry/ # Metrics and monitoring
124
- β”‚ └── validators/ # Input validation
125
- β”œβ”€β”€ pkg/ # Public packages
126
- β”‚ β”œβ”€β”€ api/ # API types and structures
127
- β”‚ β”‚ └── v0/ # Version 0 API types
128
- β”‚ └── model/ # Data models for server.json
129
- β”œβ”€β”€ scripts/ # Development and testing scripts
130
- β”œβ”€β”€ tests/ # Integration tests
131
- └── tools/ # CLI tools and utilities
132
- └── validate-*.sh # Schema validation tools
133
- ```
134
148
 
135
- ### Authentication
149
+ ### Configuration
150
+
151
+ | Method | Details |
152
+ |--------|---------|
153
+ | Environment variable | `PATHMODE_API_KEY=pm_live_...` |
154
+ | Config file | `~/.pathmode/config.json` with `apiKey`, `apiUrl`, `workspaceId` |
155
+ | Local mode | `--local` flag β€” reads `intent.md` and `.pathmode/intents/*.md` |
156
+ | No config | Intent Compiler works without any configuration |
157
+
158
+ ### Team Tools
159
+
160
+ #### Intent Management
161
+
162
+ | Tool | Description |
163
+ |------|-------------|
164
+ | `get_current_intent` | Get the active intent (first approved, or most recent) |
165
+ | `get_intent` | Get a single intent by ID with full details |
166
+ | `list_intents` | List all intents, optionally filtered by status |
167
+ | `search_intents` | Search intents by keyword across goals, objectives, and outcomes |
168
+ | `update_intent_status` | Update intent status (draft > validated > approved > shipped > verified) |
169
+ | `log_implementation_note` | Record a technical decision or implementation note |
170
+
171
+ #### Strategic Analysis
172
+
173
+ | Tool | Description |
174
+ |------|-------------|
175
+ | `analyze_intent_graph` | Analyze dependency graph for critical path, cycles, bottlenecks |
176
+ | `get_intent_relations` | Get the dependency graph for a specific intent |
177
+
178
+ #### Context & Export
179
+
180
+ | Tool | Description |
181
+ |------|-------------|
182
+ | `export_context` | Generate CLAUDE.md, .cursorrules, or intent.md files |
183
+ | `get_agent_prompt` | Get a structured execution prompt for an intent |
184
+ | `get_workspace` | Get workspace details including strategy and constitution |
185
+ | `get_constitution` | Get mandatory constraint rules for the workspace |
186
+
187
+ #### Team Prompts
188
+
189
+ | Prompt | Description |
190
+ |--------|-------------|
191
+ | `implement-intent` | Full implementation workflow for a specific intent |
192
+ | `review-risks` | Analyze the intent graph for architectural risks |
193
+ | `what-next` | Suggest the highest-priority intent to work on next |
194
+
195
+ #### Resources
196
+
197
+ | URI | Description |
198
+ |-----|-------------|
199
+ | `intent://current` | Currently active intent |
200
+ | `intent://graph` | Full intent dependency graph |
201
+ | `intent://workspace-strategy` | Workspace vision, principles, and active constitution rules |
202
+
203
+ ## Troubleshooting
204
+
205
+ **"No Pathmode configuration found"**
206
+ This no longer causes an error. The Intent Compiler works without any configuration. Team features require an API key.
207
+
208
+ **Tools return "not available in local mode"**
209
+ Most team tools require cloud mode. Set up an API key, or use `--local` for basic intent reading.
210
+
211
+ **Connection timeout**
212
+ Ensure your API key is valid and has the correct scopes. Check your network connection to `pathmode.io`.
213
+
214
+ ## Privacy Policy
215
+
216
+ This MCP server connects to the Pathmode API (`pathmode.io`) to read and write intent specifications, workspace data, and constitution rules on behalf of the authenticated user.
217
+
218
+ The **Intent Compiler** works entirely offline β€” no data is sent to Pathmode servers. Specs are saved locally to your project directory.
219
+
220
+ **Data collected (team features only):** The server transmits your API key for authentication and sends/receives workspace data via the Pathmode API.
221
+
222
+ **Data storage:** The MCP server does not store data locally (except `intent.md` files it creates and in `--local` mode). Persistent data is stored in Pathmode's cloud infrastructure.
136
223
 
137
- Publishing supports multiple authentication methods:
138
- - **GitHub OAuth** - For publishing by logging into GitHub
139
- - **GitHub OIDC** - For publishing from GitHub Actions
140
- - **DNS verification** - For proving ownership of a domain and its subdomains
141
- - **HTTP verification** - For proving ownership of a domain
224
+ **Third-party sharing:** No data is shared with third parties. The server communicates exclusively with the Pathmode API.
142
225
 
143
- The registry validates namespace ownership when publishing. E.g. to publish...:
144
- - `io.github.domdomegg/my-cool-mcp` you must login to GitHub as `domdomegg`, or be in a GitHub Action on domdomegg's repos
145
- - `me.adamjones/my-cool-mcp` you must prove ownership of `adamjones.me` via DNS or HTTP challenge
226
+ Full privacy policy: [pathmode.io/privacy](https://pathmode.io/privacy)
146
227
 
147
- ## Community Projects
228
+ ## Links
148
229
 
149
- Check out [community projects](docs/community-projects.md) to explore notable registry-related work created by the community.
230
+ - [Intent Compiler page](https://pathmode.io/intent-compiler) β€” Overview and setup guide
231
+ - [Try in browser](https://pathmode.io/sandbox) β€” Interactive sandbox, no install needed
232
+ - [Pathmode](https://pathmode.io) β€” Full platform for teams
233
+ - [Issues](https://github.com/pathmodeio/mcp-server/issues)
150
234
 
151
- ## More documentation
235
+ ## License
152
236
 
153
- See the [documentation](./docs) for more details if your question has not been answered here!
237
+ MIT
package/dist/api-client.d.ts CHANGED
@@ -10,6 +10,7 @@ export interface PathmodeConfig {
10
10
  export interface ApiIntent {
11
11
  id: string;
12
12
  workspaceId: string;
13
+ productId?: string;
13
14
  journeyId?: string;
14
15
  stageId?: string;
15
16
  stageName?: string;
@@ -26,6 +27,7 @@ export interface ApiIntent {
26
27
  constraints: string[];
27
28
  verification: Record<string, any>;
28
29
  externalLinks: any[];
30
+ evidenceAnchors: Record<string, string[]>;
29
31
  createdAt: string;
30
32
  updatedAt: string;
31
33
  shippedAt?: string;
@@ -41,6 +43,92 @@ export interface ApiIntent {
41
43
  type: string;
42
44
  }[];
43
45
  }
46
+ export interface CreateIntentInput {
47
+ title: string;
48
+ objective: string;
49
+ productId: string;
50
+ outcomes?: string[];
51
+ constraints?: string[];
52
+ healthMetrics?: string[];
53
+ edgeCases?: {
54
+ scenario: string;
55
+ expectedBehavior: string;
56
+ }[];
57
+ verification?: {
58
+ manualChecks?: string[];
59
+ unitTests?: string[];
60
+ e2eTests?: string[];
61
+ };
62
+ problemSeverity?: string;
63
+ }
64
+ export interface UpdateIntentInput {
65
+ title?: string;
66
+ objective?: string;
67
+ outcomes?: string[];
68
+ constraints?: string[];
69
+ healthMetrics?: string[];
70
+ edgeCases?: {
71
+ scenario: string;
72
+ expectedBehavior: string;
73
+ }[];
74
+ verification?: {
75
+ manualChecks?: string[];
76
+ unitTests?: string[];
77
+ e2eTests?: string[];
78
+ };
79
+ problemSeverity?: string;
80
+ evidenceAnchors?: Record<string, string[]>;
81
+ }
82
+ export interface EvidenceQuery {
83
+ productId?: string;
84
+ type?: string;
85
+ severity?: string;
86
+ tags?: string;
87
+ search?: string;
88
+ limit?: number;
89
+ }
90
+ export interface CreateEvidenceInput {
91
+ content: string;
92
+ type: string;
93
+ productId: string;
94
+ source?: string;
95
+ sourceUrl?: string;
96
+ severity?: string;
97
+ sentiment?: string;
98
+ tags?: string[];
99
+ stage?: string;
100
+ }
101
+ export interface LinkEvidenceInput {
102
+ link?: string[];
103
+ unlink?: string[];
104
+ }
105
+ export interface ApiVerificationResult {
106
+ pass: boolean;
107
+ score: number;
108
+ results: {
109
+ item: string;
110
+ category: string;
111
+ status: string;
112
+ reasoning: string;
113
+ }[];
114
+ summary: string;
115
+ }
116
+ export interface ApiEvidence {
117
+ id: string;
118
+ productId: string;
119
+ workspaceId: string;
120
+ type: string;
121
+ content: string;
122
+ source?: string;
123
+ sourceUrl?: string;
124
+ severity?: string;
125
+ sentiment?: string;
126
+ tags: string[];
127
+ stage?: string;
128
+ linkedIntentIds: string[];
129
+ createdAt: string;
130
+ updatedAt: string;
131
+ }
44
132
  export interface ApiWorkspace {
45
133
  id: string;
46
134
  name: string;
@@ -90,4 +178,18 @@ export declare class PathmodeClient {
90
178
  getConstitution(): Promise<any>;
91
179
  exportClaudeMd(): Promise<string>;
92
180
  exportContext(format: 'claude-md' | 'cursorrules' | 'intent-md', intentId?: string): Promise<string>;
181
+ createIntent(input: CreateIntentInput): Promise<ApiIntent>;
182
+ updateIntent(id: string, updates: UpdateIntentInput): Promise<ApiIntent>;
183
+ queryEvidence(filters?: EvidenceQuery): Promise<{
184
+ evidence: ApiEvidence[];
185
+ count: number;
186
+ }>;
187
+ createEvidence(input: CreateEvidenceInput): Promise<ApiEvidence>;
188
+ linkEvidence(intentId: string, body: LinkEvidenceInput): Promise<{
189
+ intentId: string;
190
+ evidenceIds: string[];
191
+ linked: number;
192
+ unlinked: number;
193
+ }>;
194
+ verifyImplementation(intentId: string, summary: string, codeChanges?: string): Promise<ApiVerificationResult>;
93
195
  }
package/dist/api-client.d.ts.map CHANGED
@@ -1 +1 @@
1
- {"version":3,"file":"","sourceRoot":"","sources":["file:///Users/jannelammi/code/Pathmode/packages/mcp-server/src/api-client.ts"],"names":[],"mappings":"AAAA;;;GAGG;AAMH,MAAM,WAAW,cAAc;IAC3B,MAAM,EAAE,MAAM,CAAC;IACf,MAAM,EAAE,MAAM,CAAC;IACf,WAAW,EAAE,MAAM,CAAC;CACvB;AAED,MAAM,WAAW,SAAS;IACtB,EAAE,EAAE,MAAM,CAAC;IACX,WAAW,EAAE,MAAM,CAAC;IACpB,SAAS,CAAC,EAAE,MAAM,CAAC;IACnB,OAAO,CAAC,EAAE,MAAM,CAAC;IACjB,SAAS,CAAC,EAAE,MAAM,CAAC;IACnB,MAAM,EAAE,MAAM,CAAC;IACf,OAAO,EAAE,MAAM,CAAC;IAChB,SAAS,EAAE,MAAM,CAAC;IAClB,eAAe,CAAC,EAAE,MAAM,CAAC;IACzB,KAAK,EAAE,MAAM,CAAC;IACd,QAAQ,EAAE,MAAM,EAAE,CAAC;IACnB,aAAa,EAAE,MAAM,EAAE,CAAC;IACxB,kBAAkB,CAAC,EAAE,MAAM,CAAC;IAC5B,cAAc,CAAC,EAAE,MAAM,CAAC;IACxB,OAAO,EAAE,MAAM,CAAC,MAAM,EAAE,GAAG,CAAC,CAAC;IAC7B,WAAW,EAAE,MAAM,EAAE,CAAC;IACtB,YAAY,EAAE,MAAM,CAAC,MAAM,EAAE,GAAG,CAAC,CAAC;IAClC,aAAa,EAAE,GAAG,EAAE,CAAC;IACrB,SAAS,EAAE,MAAM,CAAC;IAClB,SAAS,EAAE,MAAM,CAAC;IAClB,SAAS,CAAC,EAAE,MAAM,CAAC;IACnB,UAAU,CAAC,EAAE,MAAM,CAAC;IACpB,SAAS,EAAE;QAAE,EAAE,EAAE,MAAM,CAAC;QAAC,QAAQ,EAAE,MAAM,CAAC;QAAC,gBAAgB,EAAE,MAAM,CAAA;KAAE,EAAE,CAAC;IACxE,WAAW,EAAE,MAAM,EAAE,CAAC;IACtB,SAAS,EAAE;QAAE,QAAQ,EAAE,MAAM,CAAC;QAAC,IAAI,EAAE,MAAM,CAAA;KAAE,EAAE,CAAC;CACnD;AAED,MAAM,WAAW,YAAY;IACzB,EAAE,EAAE,MAAM,CAAC;IACX,IAAI,EAAE,MAAM,CAAC;IACb,MAAM,CAAC,EAAE,MAAM,CAAC;IAChB,IAAI,EAAE,MAAM,EAAE,CAAC;IACf,QAAQ,EAAE;QACN,MAAM,CAAC,EAAE,MAAM,CAAC;QAChB,SAAS,CAAC,EAAE,MAAM,EAAE,CAAC;QACrB,cAAc,CAAC,EAAE,MAAM,EAAE,CAAC;QAC1B,sBAAsB,CAAC,EAAE,MAAM,EAAE,CAAC;KACrC,GAAG,IAAI,CAAC;IACT,iBAAiB,EAAE;QACf,EAAE,EAAE,MAAM,CAAC;QACX,QAAQ,EAAE,MAAM,CAAC;QACjB,IAAI,EAAE,MAAM,CAAC;QACb,QAAQ,EAAE,OAAO,CAAC;QAClB,SAAS,EAAE,MAAM,CAAC;KACrB,EAAE,CAAC;CACP;AAKD,wBAAgB,UAAU,IAAI,cAAc,GAAG,IAAI,CAmBlD;AAED,qBAAa,cAAc;IACvB,OAAO,CAAC,MAAM,CAAS;IACvB,OAAO,CAAC,MAAM,CAAS;IACvB,OAAO,CAAC,WAAW,CAAS;gBAEhB,MAAM,EAAE,cAAc;YAMpB,KAAK;IAmBb,WAAW,CAAC,MAAM,CAAC,EAAE,MAAM,GAAG,OAAO,CAAC,SAAS,EAAE,CAAC;IAOlD,SAAS,CAAC,EAAE,EAAE,MAAM,GAAG,OAAO,CAAC,SAAS,CAAC;IAKzC,eAAe,CAAC,EAAE,EAAE,MAAM,EAAE,SAAS,SAAgB,EAAE,IAAI,SAAY,GAAG,OAAO,CAAC;QAAE,MAAM,EAAE,MAAM,CAAC;QAAC,IAAI,EAAE,MAAM,CAAA;KAAE,CAAC;IAKnH,kBAAkB,CAAC,EAAE,EAAE,MAAM,EAAE,MAAM,EAAE,MAAM,GAAG,OAAO,CAAC;QAC1D,EAAE,EAAE,MAAM,CAAC;QACX,MAAM,EAAE,MAAM,CAAC;QACf,SAAS,EAAE,MAAM,CAAC;QAClB,SAAS,CAAC,EAAE,MAAM,CAAC;QACnB,UAAU,CAAC,EAAE,MAAM,CAAC;QACpB,qBAAqB,CAAC,EAAE;YAAE,IAAI,EAAE,MAAM,CAAC;YAAC,QAAQ,EAAE,MAAM,CAAA;SAAE,EAAE,CAAC;QAC7D,0BAA0B,CAAC,EAAE,MAAM,CAAC;KACvC,CAAC;IAQI,OAAO,CAAC,QAAQ,EAAE,MAAM,EAAE,IAAI,EAAE,MAAM,EAAE,MAAM,SAAQ,GAAG,OAAO,CAAC,GAAG,CAAC;IAQrE,YAAY,IAAI,OAAO,CAAC,YAAY,CAAC;IAKrC,eAAe,IAAI,OAAO,CAAC,GAAG,CAAC;IAK/B,cAAc,IAAI,OAAO,CAAC,MAAM,CAAC;IAKjC,aAAa,CAAC,MAAM,EAAE,WAAW,GAAG,aAAa,GAAG,WAAW,EAAE,QAAQ,CAAC,EAAE,MAAM,GAAG,OAAO,CAAC,MAAM,CAAC;CAM7G"}
1
+ {"version":3,"file":"","sourceRoot":"","sources":["file:///Users/jannelammi/code/Pathmode/packages/mcp-server/src/api-client.ts"],"names":[],"mappings":"AAAA;;;GAGG;AAMH,MAAM,WAAW,cAAc;IAC3B,MAAM,EAAE,MAAM,CAAC;IACf,MAAM,EAAE,MAAM,CAAC;IACf,WAAW,EAAE,MAAM,CAAC;CACvB;AAED,MAAM,WAAW,SAAS;IACtB,EAAE,EAAE,MAAM,CAAC;IACX,WAAW,EAAE,MAAM,CAAC;IACpB,SAAS,CAAC,EAAE,MAAM,CAAC;IACnB,SAAS,CAAC,EAAE,MAAM,CAAC;IACnB,OAAO,CAAC,EAAE,MAAM,CAAC;IACjB,SAAS,CAAC,EAAE,MAAM,CAAC;IACnB,MAAM,EAAE,MAAM,CAAC;IACf,OAAO,EAAE,MAAM,CAAC;IAChB,SAAS,EAAE,MAAM,CAAC;IAClB,eAAe,CAAC,EAAE,MAAM,CAAC;IACzB,KAAK,EAAE,MAAM,CAAC;IACd,QAAQ,EAAE,MAAM,EAAE,CAAC;IACnB,aAAa,EAAE,MAAM,EAAE,CAAC;IACxB,kBAAkB,CAAC,EAAE,MAAM,CAAC;IAC5B,cAAc,CAAC,EAAE,MAAM,CAAC;IACxB,OAAO,EAAE,MAAM,CAAC,MAAM,EAAE,GAAG,CAAC,CAAC;IAC7B,WAAW,EAAE,MAAM,EAAE,CAAC;IACtB,YAAY,EAAE,MAAM,CAAC,MAAM,EAAE,GAAG,CAAC,CAAC;IAClC,aAAa,EAAE,GAAG,EAAE,CAAC;IACrB,eAAe,EAAE,MAAM,CAAC,MAAM,EAAE,MAAM,EAAE,CAAC,CAAC;IAC1C,SAAS,EAAE,MAAM,CAAC;IAClB,SAAS,EAAE,MAAM,CAAC;IAClB,SAAS,CAAC,EAAE,MAAM,CAAC;IACnB,UAAU,CAAC,EAAE,MAAM,CAAC;IACpB,SAAS,EAAE;QAAE,EAAE,EAAE,MAAM,CAAC;QAAC,QAAQ,EAAE,MAAM,CAAC;QAAC,gBAAgB,EAAE,MAAM,CAAA;KAAE,EAAE,CAAC;IACxE,WAAW,EAAE,MAAM,EAAE,CAAC;IACtB,SAAS,EAAE;QAAE,QAAQ,EAAE,MAAM,CAAC;QAAC,IAAI,EAAE,MAAM,CAAA;KAAE,EAAE,CAAC;CACnD;AAED,MAAM,WAAW,iBAAiB;IAC9B,KAAK,EAAE,MAAM,CAAC;IACd,SAAS,EAAE,MAAM,CAAC;IAClB,SAAS,EAAE,MAAM,CAAC;IAClB,QAAQ,CAAC,EAAE,MAAM,EAAE,CAAC;IACpB,WAAW,CAAC,EAAE,MAAM,EAAE,CAAC;IACvB,aAAa,CAAC,EAAE,MAAM,EAAE,CAAC;IACzB,SAAS,CAAC,EAAE;QAAE,QAAQ,EAAE,MAAM,CAAC;QAAC,gBAAgB,EAAE,MAAM,CAAA;KAAE,EAAE,CAAC;IAC7D,YAAY,CAAC,EAAE;QAAE,YAAY,CAAC,EAAE,MAAM,EAAE,CAAC;QAAC,SAAS,CAAC,EAAE,MAAM,EAAE,CAAC;QAAC,QAAQ,CAAC,EAAE,MAAM,EAAE,CAAA;KAAE,CAAC;IACtF,eAAe,CAAC,EAAE,MAAM,CAAC;CAC5B;AAED,MAAM,WAAW,iBAAiB;IAC9B,KAAK,CAAC,EAAE,MAAM,CAAC;IACf,SAAS,CAAC,EAAE,MAAM,CAAC;IACnB,QAAQ,CAAC,EAAE,MAAM,EAAE,CAAC;IACpB,WAAW,CAAC,EAAE,MAAM,EAAE,CAAC;IACvB,aAAa,CAAC,EAAE,MAAM,EAAE,CAAC;IACzB,SAAS,CAAC,EAAE;QAAE,QAAQ,EAAE,MAAM,CAAC;QAAC,gBAAgB,EAAE,MAAM,CAAA;KAAE,EAAE,CAAC;IAC7D,YAAY,CAAC,EAAE;QAAE,YAAY,CAAC,EAAE,MAAM,EAAE,CAAC;QAAC,SAAS,CAAC,EAAE,MAAM,EAAE,CAAC;QAAC,QAAQ,CAAC,EAAE,MAAM,EAAE,CAAA;KAAE,CAAC;IACtF,eAAe,CAAC,EAAE,MAAM,CAAC;IACzB,eAAe,CAAC,EAAE,MAAM,CAAC,MAAM,EAAE,MAAM,EAAE,CAAC,CAAC;CAC9C;AAED,MAAM,WAAW,aAAa;IAC1B,SAAS,CAAC,EAAE,MAAM,CAAC;IACnB,IAAI,CAAC,EAAE,MAAM,CAAC;IACd,QAAQ,CAAC,EAAE,MAAM,CAAC;IAClB,IAAI,CAAC,EAAE,MAAM,CAAC;IACd,MAAM,CAAC,EAAE,MAAM,CAAC;IAChB,KAAK,CAAC,EAAE,MAAM,CAAC;CAClB;AAED,MAAM,WAAW,mBAAmB;IAChC,OAAO,EAAE,MAAM,CAAC;IAChB,IAAI,EAAE,MAAM,CAAC;IACb,SAAS,EAAE,MAAM,CAAC;IAClB,MAAM,CAAC,EAAE,MAAM,CAAC;IAChB,SAAS,CAAC,EAAE,MAAM,CAAC;IACnB,QAAQ,CAAC,EAAE,MAAM,CAAC;IAClB,SAAS,CAAC,EAAE,MAAM,CAAC;IACnB,IAAI,CAAC,EAAE,MAAM,EAAE,CAAC;IAChB,KAAK,CAAC,EAAE,MAAM,CAAC;CAClB;AAED,MAAM,WAAW,iBAAiB;IAC9B,IAAI,CAAC,EAAE,MAAM,EAAE,CAAC;IAChB,MAAM,CAAC,EAAE,MAAM,EAAE,CAAC;CACrB;AAED,MAAM,WAAW,qBAAqB;IAClC,IAAI,EAAE,OAAO,CAAC;IACd,KAAK,EAAE,MAAM,CAAC;IACd,OAAO,EAAE;QAAE,IAAI,EAAE,MAAM,CAAC;QAAC,QAAQ,EAAE,MAAM,CAAC;QAAC,MAAM,EAAE,MAAM,CAAC;QAAC,SAAS,EAAE,MAAM,CAAA;KAAE,EAAE,CAAC;IACjF,OAAO,EAAE,MAAM,CAAC;CACnB;AAED,MAAM,WAAW,WAAW;IACxB,EAAE,EAAE,MAAM,CAAC;IACX,SAAS,EAAE,MAAM,CAAC;IAClB,WAAW,EAAE,MAAM,CAAC;IACpB,IAAI,EAAE,MAAM,CAAC;IACb,OAAO,EAAE,MAAM,CAAC;IAChB,MAAM,CAAC,EAAE,MAAM,CAAC;IAChB,SAAS,CAAC,EAAE,MAAM,CAAC;IACnB,QAAQ,CAAC,EAAE,MAAM,CAAC;IAClB,SAAS,CAAC,EAAE,MAAM,CAAC;IACnB,IAAI,EAAE,MAAM,EAAE,CAAC;IACf,KAAK,CAAC,EAAE,MAAM,CAAC;IACf,eAAe,EAAE,MAAM,EAAE,CAAC;IAC1B,SAAS,EAAE,MAAM,CAAC;IAClB,SAAS,EAAE,MAAM,CAAC;CACrB;AAED,MAAM,WAAW,YAAY;IACzB,EAAE,EAAE,MAAM,CAAC;IACX,IAAI,EAAE,MAAM,CAAC;IACb,MAAM,CAAC,EAAE,MAAM,CAAC;IAChB,IAAI,EAAE,MAAM,EAAE,CAAC;IACf,QAAQ,EAAE;QACN,MAAM,CAAC,EAAE,MAAM,CAAC;QAChB,SAAS,CAAC,EAAE,MAAM,EAAE,CAAC;QACrB,cAAc,CAAC,EAAE,MAAM,EAAE,CAAC;QAC1B,sBAAsB,CAAC,EAAE,MAAM,EAAE,CAAC;KACrC,GAAG,IAAI,CAAC;IACT,iBAAiB,EAAE;QACf,EAAE,EAAE,MAAM,CAAC;QACX,QAAQ,EAAE,MAAM,CAAC;QACjB,IAAI,EAAE,MAAM,CAAC;QACb,QAAQ,EAAE,OAAO,CAAC;QAClB,SAAS,EAAE,MAAM,CAAC;KACrB,EAAE,CAAC;CACP;AAKD,wBAAgB,UAAU,IAAI,cAAc,GAAG,IAAI,CAmBlD;AAED,qBAAa,cAAc;IACvB,OAAO,CAAC,MAAM,CAAS;IACvB,OAAO,CAAC,MAAM,CAAS;IACvB,OAAO,CAAC,WAAW,CAAS;gBAEhB,MAAM,EAAE,cAAc;YAMpB,KAAK;IAqBb,WAAW,CAAC,MAAM,CAAC,EAAE,MAAM,GAAG,OAAO,CAAC,SAAS,EAAE,CAAC;IAOlD,SAAS,CAAC,EAAE,EAAE,MAAM,GAAG,OAAO,CAAC,SAAS,CAAC;IAKzC,eAAe,CAAC,EAAE,EAAE,MAAM,EAAE,SAAS,SAAgB,EAAE,IAAI,SAAY,GAAG,OAAO,CAAC;QAAE,MAAM,EAAE,MAAM,CAAC;QAAC,IAAI,EAAE,MAAM,CAAA;KAAE,CAAC;IAKnH,kBAAkB,CAAC,EAAE,EAAE,MAAM,EAAE,MAAM,EAAE,MAAM,GAAG,OAAO,CAAC;QAC1D,EAAE,EAAE,MAAM,CAAC;QACX,MAAM,EAAE,MAAM,CAAC;QACf,SAAS,EAAE,MAAM,CAAC;QAClB,SAAS,CAAC,EAAE,MAAM,CAAC;QACnB,UAAU,CAAC,EAAE,MAAM,CAAC;QACpB,qBAAqB,CAAC,EAAE;YAAE,IAAI,EAAE,MAAM,CAAC;YAAC,QAAQ,EAAE,MAAM,CAAA;SAAE,EAAE,CAAC;QAC7D,0BAA0B,CAAC,EAAE,MAAM,CAAC;KACvC,CAAC;IAQI,OAAO,CAAC,QAAQ,EAAE,MAAM,EAAE,IAAI,EAAE,MAAM,EAAE,MAAM,SAAQ,GAAG,OAAO,CAAC,GAAG,CAAC;IAQrE,YAAY,IAAI,OAAO,CAAC,YAAY,CAAC;IAKrC,eAAe,IAAI,OAAO,CAAC,GAAG,CAAC;IAK/B,cAAc,IAAI,OAAO,CAAC,MAAM,CAAC;IAKjC,aAAa,CAAC,MAAM,EAAE,WAAW,GAAG,aAAa,GAAG,WAAW,EAAE,QAAQ,CAAC,EAAE,MAAM,GAAG,OAAO,CAAC,MAAM,CAAC;IASpG,YAAY,CAAC,KAAK,EAAE,iBAAiB,GAAG,OAAO,CAAC,SAAS,CAAC;IAQ1D,YAAY,CAAC,EAAE,EAAE,MAAM,EAAE,OAAO,EAAE,iBAAiB,GAAG,OAAO,CAAC,SAAS,CAAC;IAQxE,aAAa,CAAC,OAAO,GAAE,aAAkB,GAAG,OAAO,CAAC;QAAE,QAAQ,EAAE,WAAW,EAAE,CAAC;QAAC,KAAK,EAAE,MAAM,CAAA;KAAE,CAAC;IAU/F,cAAc,CAAC,KAAK,EAAE,mBAAmB,GAAG,OAAO,CAAC,WAAW,CAAC;IAQhE,YAAY,CAAC,QAAQ,EAAE,MAAM,EAAE,IAAI,EAAE,iBAAiB,GAAG,OAAO,CAAC;QAAE,QAAQ,EAAE,MAAM,CAAC;QAAC,WAAW,EAAE,MAAM,EAAE,CAAC;QAAC,MAAM,EAAE,MAAM,CAAC;QAAC,QAAQ,EAAE,MAAM,CAAA;KAAE,CAAC;IAQ/I,oBAAoB,CAAC,QAAQ,EAAE,MAAM,EAAE,OAAO,EAAE,MAAM,EAAE,WAAW,CAAC,EAAE,MAAM,GAAG,OAAO,CAAC,qBAAqB,CAAC;CAOtH"}
package/dist/index.js CHANGED
@@ -11403,6 +11403,7 @@ class PathmodeClient {
11403
11403
  }
11404
11404
  async fetch(path, options = {}) {
11405
11405
  const url = `${this.apiUrl}/api/v1${path}`;
11406
+ console.error(`[pathmode-mcp] fetch: ${url}, key prefix: ${this.apiKey.substring(0, 16)}`);
11406
11407
  const response = await fetch(url, {
11407
11408
  ...options,
11408
11409
  headers: {
@@ -11413,6 +11414,7 @@ class PathmodeClient {
11413
11414
  });
11414
11415
  if (!response.ok) {
11415
11416
  const body = await response.json().catch(() => ({ error: response.statusText }));
11417
+ console.error(`[pathmode-mcp] ${response.status}: ${JSON.stringify(body)}, key length: ${this.apiKey.length}`);
11416
11418
  throw new Error(`API error (${response.status}): ${body.error || response.statusText}`);
11417
11419
  }
11418
11420
  return response;
@@ -11464,6 +11466,52 @@ class PathmodeClient {
11464
11466
  const res = await this.fetch(`/export?${params.toString()}`);
11465
11467
  return res.text();
11466
11468
  }
11469
+ // --- Write operations (v1.3.0) ---
11470
+ async createIntent(input) {
11471
+ const res = await this.fetch('/intents', {
11472
+ method: 'POST',
11473
+ body: JSON.stringify(input),
11474
+ });
11475
+ return res.json();
11476
+ }
11477
+ async updateIntent(id, updates) {
11478
+ const res = await this.fetch(`/intents/${id}`, {
11479
+ method: 'PATCH',
11480
+ body: JSON.stringify(updates),
11481
+ });
11482
+ return res.json();
11483
+ }
11484
+ async queryEvidence(filters = {}) {
11485
+ const params = new URLSearchParams();
11486
+ for (const [key, val] of Object.entries(filters)) {
11487
+ if (val !== undefined && val !== null)
11488
+ params.set(key, String(val));
11489
+ }
11490
+ const qs = params.toString();
11491
+ const res = await this.fetch(`/evidence${qs ? `?${qs}` : ''}`);
11492
+ return res.json();
11493
+ }
11494
+ async createEvidence(input) {
11495
+ const res = await this.fetch('/evidence', {
11496
+ method: 'POST',
11497
+ body: JSON.stringify(input),
11498
+ });
11499
+ return res.json();
11500
+ }
11501
+ async linkEvidence(intentId, body) {
11502
+ const res = await this.fetch(`/intents/${intentId}/evidence`, {
11503
+ method: 'POST',
11504
+ body: JSON.stringify(body),
11505
+ });
11506
+ return res.json();
11507
+ }
11508
+ async verifyImplementation(intentId, summary, codeChanges) {
11509
+ const res = await this.fetch(`/intents/${intentId}/verify`, {
11510
+ method: 'POST',
11511
+ body: JSON.stringify({ summary, codeChanges }),
11512
+ });
11513
+ return res.json();
11514
+ }
11467
11515
  }
11468
11516
  exports.PathmodeClient = PathmodeClient;
11469
11517
 
@@ -39709,6 +39757,7 @@ const isLocalMode = process.argv.includes('--local');
39709
39757
  let client = null;
39710
39758
  if (!isLocalMode) {
39711
39759
  const config = (0, api_client_1.loadConfig)();
39760
+ console.error(`[pathmode-mcp] API key present: ${!!config?.apiKey}, prefix: ${config?.apiKey?.substring(0, 16) || 'none'}, url: ${config?.apiUrl || 'none'}`);
39712
39761
  if (config) {
39713
39762
  client = new api_client_1.PathmodeClient(config);
39714
39763
  }
@@ -39719,7 +39768,7 @@ if (!isLocalMode) {
39719
39768
  // ============================================================
39720
39769
  const server = new mcp_js_1.McpServer({
39721
39770
  name: 'pathmode',
39722
- version: '1.2.0',
39771
+ version: '1.3.0',
39723
39772
  });
39724
39773
  // Annotation presets
39725
39774
  const READ_ONLY = { readOnlyHint: true, openWorldHint: true };
@@ -40164,6 +40213,179 @@ server.registerTool('log_implementation_note', {
40164
40213
  }]
40165
40214
  };
40166
40215
  });
40216
+ server.registerTool('create_intent', {
40217
+ title: 'Create Intent',
40218
+ description: 'Create a new intent spec in the workspace. Requires at minimum a title, objective, and productId. Returns the created intent with its ID. Use list_intents first to see existing intents and avoid duplicates.',
40219
+ inputSchema: {
40220
+ title: zod_1.z.string().describe('Short name for the intent (e.g., "Improve onboarding flow")'),
40221
+ objective: zod_1.z.string().describe('Why this matters β€” the problem and who has it'),
40222
+ productId: zod_1.z.string().describe('Product (Space) ID this intent belongs to. Use get_workspace to find product IDs.'),
40223
+ outcomes: zod_1.z.array(zod_1.z.string()).optional().describe('Observable, testable state changes'),
40224
+ constraints: zod_1.z.array(zod_1.z.string()).optional().describe('Hard limits the implementation must respect'),
40225
+ healthMetrics: zod_1.z.array(zod_1.z.string()).optional().describe('What to monitor after shipping'),
40226
+ edgeCases: zod_1.z.array(zod_1.z.object({
40227
+ scenario: zod_1.z.string(),
40228
+ expectedBehavior: zod_1.z.string(),
40229
+ })).optional().describe('Failure modes and boundary conditions'),
40230
+ verification: zod_1.z.object({
40231
+ manualChecks: zod_1.z.array(zod_1.z.string()).optional(),
40232
+ unitTests: zod_1.z.array(zod_1.z.string()).optional(),
40233
+ e2eTests: zod_1.z.array(zod_1.z.string()).optional(),
40234
+ }).optional().describe('How to confirm it works'),
40235
+ problemSeverity: zod_1.z.enum(['low', 'medium', 'high', 'critical']).optional().describe('How severe the problem is'),
40236
+ },
40237
+ annotations: WRITE_OP,
40238
+ }, async ({ productId, ...rest }) => {
40239
+ if (isLocalMode) {
40240
+ return { content: [{ type: 'text', text: 'Creating intents requires cloud mode. Use PATHMODE_API_KEY to connect.' }] };
40241
+ }
40242
+ const result = await client.createIntent({ productId, ...rest });
40243
+ return {
40244
+ content: [{
40245
+ type: 'text',
40246
+ text: `Intent created: ${result.id}\nTitle: "${result.title}"\nStatus: ${result.status}\nProduct: ${result.productId || productId}`
40247
+ }]
40248
+ };
40249
+ });
40250
+ server.registerTool('update_intent', {
40251
+ title: 'Update Intent',
40252
+ description: "Update an existing intent's content. Provide only the fields you want to change. Does NOT change intent status (use update_intent_status for that).",
40253
+ inputSchema: {
40254
+ intentId: zod_1.z.string().describe('The intent ID to update'),
40255
+ title: zod_1.z.string().optional().describe('New title'),
40256
+ objective: zod_1.z.string().optional().describe('Updated objective'),
40257
+ outcomes: zod_1.z.array(zod_1.z.string()).optional().describe('Replace all outcomes'),
40258
+ constraints: zod_1.z.array(zod_1.z.string()).optional().describe('Replace all constraints'),
40259
+ healthMetrics: zod_1.z.array(zod_1.z.string()).optional().describe('Replace all health metrics'),
40260
+ edgeCases: zod_1.z.array(zod_1.z.object({
40261
+ scenario: zod_1.z.string(),
40262
+ expectedBehavior: zod_1.z.string(),
40263
+ })).optional().describe('Replace all edge cases'),
40264
+ verification: zod_1.z.object({
40265
+ manualChecks: zod_1.z.array(zod_1.z.string()).optional(),
40266
+ unitTests: zod_1.z.array(zod_1.z.string()).optional(),
40267
+ e2eTests: zod_1.z.array(zod_1.z.string()).optional(),
40268
+ }).optional().describe('Replace verification plan'),
40269
+ problemSeverity: zod_1.z.enum(['low', 'medium', 'high', 'critical']).optional(),
40270
+ },
40271
+ annotations: { ...WRITE_OP, idempotentHint: true },
40272
+ }, async ({ intentId, ...updates }) => {
40273
+ if (isLocalMode) {
40274
+ return { content: [{ type: 'text', text: 'Updating intents requires cloud mode.' }] };
40275
+ }
40276
+ const result = await client.updateIntent(intentId, updates);
40277
+ const changedFields = Object.keys(updates).filter(k => updates[k] !== undefined);
40278
+ return {
40279
+ content: [{
40280
+ type: 'text',
40281
+ text: `Intent ${intentId} updated. Fields changed: ${changedFields.join(', ')}`
40282
+ }]
40283
+ };
40284
+ });
40285
+ server.registerTool('query_evidence', {
40286
+ title: 'Query Evidence',
40287
+ description: 'Search evidence items (friction points, user quotes, observations, metrics, feature requests) by product, type, severity, or text. Returns matching evidence with IDs that can be linked to intents.',
40288
+ inputSchema: {
40289
+ productId: zod_1.z.string().optional().describe('Filter by product (Space) ID'),
40290
+ type: zod_1.z.enum(['friction', 'quote', 'observation', 'metric', 'request']).optional().describe('Filter by evidence type'),
40291
+ severity: zod_1.z.enum(['low', 'medium', 'high', 'critical']).optional().describe('Filter by severity'),
40292
+ search: zod_1.z.string().optional().describe('Text search across evidence content'),
40293
+ tags: zod_1.z.string().optional().describe('Comma-separated tags to filter by'),
40294
+ limit: zod_1.z.number().optional().describe('Max results (default 50, max 200)'),
40295
+ },
40296
+ annotations: READ_ONLY,
40297
+ }, async (filters) => {
40298
+ if (isLocalMode) {
40299
+ return { content: [{ type: 'text', text: 'Evidence queries require cloud mode.' }] };
40300
+ }
40301
+ const result = await client.queryEvidence(filters);
40302
+ return {
40303
+ content: [{
40304
+ type: 'text',
40305
+ text: JSON.stringify(result, null, 2)
40306
+ }]
40307
+ };
40308
+ });
40309
+ server.registerTool('create_evidence', {
40310
+ title: 'Create Evidence',
40311
+ description: 'Create a new evidence item (e.g., a discovered bug, user feedback quote, behavioral observation, or feature request). Evidence can later be linked to intents to support prioritization.',
40312
+ inputSchema: {
40313
+ content: zod_1.z.string().describe('The evidence content β€” a finding, quote, or observation'),
40314
+ type: zod_1.z.enum(['friction', 'quote', 'observation', 'metric', 'request']).describe('Type of evidence'),
40315
+ productId: zod_1.z.string().describe('Product (Space) ID this evidence belongs to'),
40316
+ source: zod_1.z.string().optional().describe('Where this evidence came from (e.g., "User interview", "Bug report", "Support ticket")'),
40317
+ sourceUrl: zod_1.z.string().optional().describe('URL to the original source'),
40318
+ severity: zod_1.z.enum(['low', 'medium', 'high', 'critical']).optional().describe('Severity level (required for friction type)'),
40319
+ sentiment: zod_1.z.enum(['positive', 'negative', 'neutral', 'mixed']).optional().describe('Emotional sentiment'),
40320
+ tags: zod_1.z.array(zod_1.z.string()).optional().describe('Category tags (e.g., ["Onboarding", "Performance"])'),
40321
+ stage: zod_1.z.string().optional().describe('User journey stage (e.g., "Discovery", "Checkout")'),
40322
+ },
40323
+ annotations: WRITE_OP,
40324
+ }, async ({ productId, ...rest }) => {
40325
+ if (isLocalMode) {
40326
+ return { content: [{ type: 'text', text: 'Creating evidence requires cloud mode.' }] };
40327
+ }
40328
+ const result = await client.createEvidence({ productId, ...rest });
40329
+ return {
40330
+ content: [{
40331
+ type: 'text',
40332
+ text: `Evidence created: ${result.id}\nType: ${result.type}\nContent: "${(result.content || '').slice(0, 80)}${(result.content || '').length > 80 ? '...' : ''}"`
40333
+ }]
40334
+ };
40335
+ });
40336
+ server.registerTool('link_evidence', {
40337
+ title: 'Link Evidence to Intent',
40338
+ description: 'Link or unlink evidence items to/from an intent. Linking evidence to intents establishes traceability between user problems and planned solutions.',
40339
+ inputSchema: {
40340
+ intentId: zod_1.z.string().describe('The intent ID to link evidence to'),
40341
+ link: zod_1.z.array(zod_1.z.string()).optional().describe('Evidence IDs to link to this intent'),
40342
+ unlink: zod_1.z.array(zod_1.z.string()).optional().describe('Evidence IDs to unlink from this intent'),
40343
+ },
40344
+ annotations: WRITE_OP,
40345
+ }, async ({ intentId, link, unlink }) => {
40346
+ if (isLocalMode) {
40347
+ return { content: [{ type: 'text', text: 'Evidence linking requires cloud mode.' }] };
40348
+ }
40349
+ const result = await client.linkEvidence(intentId, { link, unlink });
40350
+ const actions = [];
40351
+ if (link && link.length > 0)
40352
+ actions.push(`linked ${result.linked} evidence items`);
40353
+ if (unlink && unlink.length > 0)
40354
+ actions.push(`unlinked ${result.unlinked} evidence items`);
40355
+ return {
40356
+ content: [{
40357
+ type: 'text',
40358
+ text: `Intent ${intentId}: ${actions.join(', ')}. Total evidence linked: ${result.evidenceIds.length}`
40359
+ }]
40360
+ };
40361
+ });
40362
+ server.registerTool('verify_implementation', {
40363
+ title: 'Verify Implementation',
40364
+ description: 'AI-grade your implementation against the intent spec. Checks each outcome, constraint, constitution rule, and edge case. Returns pass/fail per item with reasoning and an overall score. Also logs the result as an implementation note.',
40365
+ inputSchema: {
40366
+ intentId: zod_1.z.string().describe('The intent ID to verify against'),
40367
+ summary: zod_1.z.string().describe('Description of what was implemented and how'),
40368
+ codeChanges: zod_1.z.string().optional().describe('Summary of code changes (file list, key modifications)'),
40369
+ },
40370
+ annotations: WRITE_OP,
40371
+ }, async ({ intentId, summary, codeChanges }) => {
40372
+ if (isLocalMode) {
40373
+ return { content: [{ type: 'text', text: 'Verification requires cloud mode.' }] };
40374
+ }
40375
+ try {
40376
+ const result = await client.verifyImplementation(intentId, summary, codeChanges);
40377
+ let text = `Verification ${result.pass ? 'PASSED' : 'FAILED'} (score: ${result.score}/100)\n\n`;
40378
+ text += `${result.summary}\n\n`;
40379
+ for (const r of result.results) {
40380
+ const icon = r.status === 'pass' ? '[PASS]' : r.status === 'fail' ? '[FAIL]' : '[????]';
40381
+ text += `${icon} [${r.category}] ${r.item}\n ${r.reasoning}\n`;
40382
+ }
40383
+ return { content: [{ type: 'text', text }] };
40384
+ }
40385
+ catch (e) {
40386
+ return { content: [{ type: 'text', text: `Verification failed: ${e.message}` }] };
40387
+ }
40388
+ });
40167
40389
  // ============================================================
40168
40390
  // Prompts
40169
40391
  // ============================================================
@@ -40175,7 +40397,7 @@ server.prompt('implement-intent', 'Get full implementation context for a specifi
40175
40397
  role: 'user',
40176
40398
  content: {
40177
40399
  type: 'text',
40178
- text: `I need to implement intent ${intentId}. Please:\n1. Use the get_agent_prompt tool to fetch the full execution prompt for this intent\n2. Use get_constitution to check for workspace constraints I must respect\n3. Review the intent details and create an implementation plan\n4. After implementation, use update_intent_status to mark it as "shipped"\n5. Use log_implementation_note to document key technical decisions`,
40400
+ text: `I need to implement intent ${intentId}. Please:\n1. Use the get_agent_prompt tool to fetch the full execution prompt for this intent\n2. Use get_constitution to check for workspace constraints I must respect\n3. Review the intent details and create an implementation plan\n4. After implementation, use verify_implementation to AI-grade your work against the spec\n5. If verification passes, use update_intent_status to mark it as "shipped"\n6. Use log_implementation_note to document key technical decisions`,
40179
40401
  },
40180
40402
  }],
40181
40403
  };
@@ -40202,6 +40424,19 @@ server.prompt('what-next', 'Suggest the highest-priority intent to work on next,
40202
40424
  }],
40203
40425
  };
40204
40426
  });
40427
+ server.prompt('create-from-evidence', 'Search for evidence items, identify patterns, and create an intent based on the strongest evidence cluster.', {
40428
+ productId: zod_1.z.string().describe('The product ID to search evidence for'),
40429
+ }, async ({ productId }) => {
40430
+ return {
40431
+ messages: [{
40432
+ role: 'user',
40433
+ content: {
40434
+ type: 'text',
40435
+ text: `Help me create a new intent from evidence:\n1. Use query_evidence with productId "${productId}" to see what evidence exists\n2. Look for patterns β€” multiple friction points about the same issue, or high-severity items\n3. Propose an intent based on the strongest evidence cluster\n4. Use create_intent to create the intent\n5. Use link_evidence to link the relevant evidence items to the new intent`,
40436
+ },
40437
+ }],
40438
+ };
40439
+ });
40205
40440
  // ============================================================
40206
40441
  // Intent Compiler β€” Zero-config tools (no API key needed)
40207
40442
  // ============================================================
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@pathmode/mcp-server",
3
- "version": "1.2.2",
3
+ "version": "1.3.0",
4
4
  "mcpName": "io.github.pathmodeio/mcp-server",
5
5
  "description": "Pathmode MCP Server β€” Build structured intent specs through Socratic AI conversation (zero-config), or connect to your Intent Layer for strategic context, dependency graphs, and implementation prompts.",
6
6
  "main": "dist/index.js",