nodestorm-mcp 0.1.0 → 0.1.1

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 (2) hide show
  1. package/README.md +54 -24
  2. package/package.json +3 -3
package/README.md CHANGED
@@ -1,27 +1,26 @@
1
1
  # nodestorm-mcp
2
2
 
3
- MCP (Model Context Protocol) server for NodeStorm workflow automation.
3
+ MCP (Model Context Protocol) server for [NodeStorm](https://nodestorm.ai) workflow automation.
4
4
 
5
5
  ## Installation
6
6
 
7
- ```bash
8
- npx nodestorm-mcp
9
- ```
10
-
11
- Or install globally:
7
+ No install step needed — MCP clients run it via `npx`:
12
8
 
13
9
  ```bash
14
- npm install -g nodestorm-mcp
10
+ npx -y nodestorm-mcp
15
11
  ```
16
12
 
17
13
  ## Configuration
18
14
 
19
- ### Claude Code / Claude Desktop
15
+ ### Claude Code
16
+
17
+ From your project directory:
20
18
 
21
- Add to your Claude configuration file:
19
+ ```bash
20
+ claude mcp add nodestorm -e NODESTORM_API_KEY=ns_your_access_token_here -- npx -y nodestorm-mcp
21
+ ```
22
22
 
23
- **macOS**: `~/Library/Application Support/Claude/claude_desktop_config.json`
24
- **Windows**: `%APPDATA%\Claude\claude_desktop_config.json`
23
+ Or add to a `.mcp.json` in your project root (or `~/.claude.json` for all projects):
25
24
 
26
25
  ```json
27
26
  {
@@ -37,6 +36,13 @@ Add to your Claude configuration file:
37
36
  }
38
37
  ```
39
38
 
39
+ ### Claude Desktop
40
+
41
+ Add the same `mcpServers` block to:
42
+
43
+ - **macOS**: `~/Library/Application Support/Claude/claude_desktop_config.json`
44
+ - **Windows**: `%APPDATA%\Claude\claude_desktop_config.json`
45
+
40
46
  ### Environment Variables
41
47
 
42
48
  | Variable | Required | Description |
@@ -72,10 +78,18 @@ Output: { id, name, nodes, edges, url, updated_at }
72
78
  ```
73
79
 
74
80
  ### update_flow
75
- Modify an existing workflow.
81
+ Update workflow **metadata** (name, description, schedule). Does not modify nodes or edges — use `update_flow_structure` for that.
76
82
 
77
83
  ```
78
- Input: { id: "abc123", flow: { name, nodes, edges } }
84
+ Input: { id: "abc123", flow: { name, description, schedule_enabled, ... } }
85
+ Output: { id, name, nodes, edges, url, updated_at }
86
+ ```
87
+
88
+ ### update_flow_structure
89
+ Apply a list of structural operations (add/update/remove nodes and edges) atomically to an existing workflow.
90
+
91
+ ```
92
+ Input: { flow_id: "abc123", operations: [{ op: "add_node", ... }, ...] }
79
93
  Output: { id, name, nodes, edges, url, updated_at }
80
94
  ```
81
95
 
@@ -88,21 +102,13 @@ Output: { success: true }
88
102
  ```
89
103
 
90
104
  ### list_flows
91
- List all your workflows.
105
+ List or search your workflows (`scope: "public"` searches published community entries).
92
106
 
93
107
  ```
94
- Input: { limit: 20, offset: 0 }
108
+ Input: { query: "pricing", scope: "user", limit: 20 }
95
109
  Output: { flows: [...], total }
96
110
  ```
97
111
 
98
- ### validate_flow
99
- Check if a workflow is valid before saving.
100
-
101
- ```
102
- Input: { flow: { nodes, edges } }
103
- Output: { valid: true } or { valid: false, errors: [...] }
104
- ```
105
-
106
112
  ### describe_nodes
107
113
  Get node type definitions (no API call).
108
114
 
@@ -111,6 +117,30 @@ Input: { types: ["prompt", "list"] } // optional filter
111
117
  Output: { nodes: [{ type, description, category, config_schema, handles }] }
112
118
  ```
113
119
 
120
+ ### get_flow_run
121
+ Get details of a specific flow run, including execution results and node outputs.
122
+
123
+ ```
124
+ Input: { id: "run123" }
125
+ Output: { id, flow_id, status, node_results, started_at, finished_at }
126
+ ```
127
+
128
+ ### list_flow_runs
129
+ List flow runs with optional filters, for debugging and monitoring.
130
+
131
+ ```
132
+ Input: { flow_id: "abc123", status: "failed", limit: 20 }
133
+ Output: { runs: [...], total }
134
+ ```
135
+
136
+ ### search_chat_history
137
+ Semantic (meaning-based) search over your past NodeStorm chat messages.
138
+
139
+ ```
140
+ Input: { query: "how did I set up the scraper flow", limit: 10 }
141
+ Output: { messages: [...] }
142
+ ```
143
+
114
144
  ## Resources
115
145
 
116
146
  ### workflow-guide
@@ -131,7 +161,7 @@ Created "Competitor Pricing Analysis"
131
161
 
132
162
  User: Add 3 more URLs to the list
133
163
 
134
- Claude: [Uses get_flow, modifies nodes, uses update_flow]
164
+ Claude: [Uses update_flow_structure with add_node/add_edge operations]
135
165
  Updated flow with 3 additional URLs.
136
166
  ```
137
167
 
package/package.json CHANGED
@@ -1,10 +1,10 @@
1
1
  {
2
2
  "name": "nodestorm-mcp",
3
- "version": "0.1.0",
3
+ "version": "0.1.1",
4
4
  "description": "MCP server for NodeStorm workflow automation",
5
5
  "type": "module",
6
6
  "bin": {
7
- "nodestorm-mcp": "./dist/index.js"
7
+ "nodestorm-mcp": "dist/index.js"
8
8
  },
9
9
  "main": "./dist/index.js",
10
10
  "types": "./dist/index.d.ts",
@@ -31,7 +31,7 @@
31
31
  "license": "MIT",
32
32
  "repository": {
33
33
  "type": "git",
34
- "url": "https://github.com/nodestorm/nodestorm-mcp"
34
+ "url": "git+https://github.com/nodestorm/nodestorm-mcp.git"
35
35
  },
36
36
  "dependencies": {
37
37
  "@modelcontextprotocol/sdk": "^1.0.0"