@contextstream/mcp-server 0.4.80 → 0.4.81
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.
- package/README.md +149 -184
- package/dist/index.js +20496 -20343
- package/package.json +19 -3
package/README.md
CHANGED
|
@@ -1,142 +1,169 @@
|
|
|
1
1
|
<p align="center">
|
|
2
|
-
<img src="https://contextstream.io/400logo.png" alt="ContextStream" width="80" />
|
|
2
|
+
<img src="https://contextstream.io/400logo.png" alt="ContextStream — persistent memory and semantic code search for AI coding assistants" width="80" />
|
|
3
3
|
</p>
|
|
4
4
|
|
|
5
5
|
<h1 align="center">ContextStream MCP Server</h1>
|
|
6
6
|
|
|
7
7
|
<p align="center">
|
|
8
|
-
<strong>
|
|
8
|
+
<strong>Persistent memory, semantic code search, and team context for Claude Code, Cursor, VS Code Copilot, Windsurf — and every MCP-compatible AI coding assistant.</strong>
|
|
9
|
+
</p>
|
|
10
|
+
|
|
11
|
+
<p align="center">
|
|
12
|
+
🏆 <b>90.0% on LongMemEval-S</b> — the full 500-instance suite with the official judge.<br/>
|
|
13
|
+
Beats supermemory with statistical significance; matches Zep. <a href="https://contextstream.io/benchmarks">See the benchmarks →</a>
|
|
9
14
|
</p>
|
|
10
15
|
|
|
11
16
|
<p align="center">
|
|
12
17
|
<a href="https://www.npmjs.com/package/@contextstream/mcp-server"><img src="https://img.shields.io/npm/v/@contextstream/mcp-server.svg" alt="npm version" /></a>
|
|
13
|
-
<a href="https://www.npmjs.com/package/@contextstream/mcp-server"><img src="https://img.shields.io/npm/dm/@contextstream/mcp-server.svg" alt="downloads" /></a>
|
|
14
|
-
<a href="https://github.com/contextstream/mcp-server/blob/main/LICENSE"><img src="https://img.shields.io/npm/l/@contextstream/mcp-server.svg" alt="license" /></a>
|
|
18
|
+
<a href="https://www.npmjs.com/package/@contextstream/mcp-server"><img src="https://img.shields.io/npm/dm/@contextstream/mcp-server.svg" alt="npm downloads" /></a>
|
|
19
|
+
<a href="https://github.com/contextstream/mcp-server/blob/main/LICENSE"><img src="https://img.shields.io/npm/l/@contextstream/mcp-server.svg" alt="MIT license" /></a>
|
|
20
|
+
<img src="https://img.shields.io/node/v/@contextstream/mcp-server.svg" alt="node version" />
|
|
15
21
|
</p>
|
|
16
22
|
|
|
17
23
|
<p align="center">
|
|
18
24
|
<a href="https://contextstream.io/docs">Documentation</a> •
|
|
19
|
-
<a href="https://contextstream.io/pricing">Pricing</a>
|
|
25
|
+
<a href="https://contextstream.io/pricing">Pricing</a> •
|
|
26
|
+
<a href="#faq">FAQ</a>
|
|
20
27
|
</p>
|
|
21
28
|
|
|
22
29
|
---
|
|
23
30
|
|
|
24
|
-
|
|
31
|
+
## Try it in 30 seconds
|
|
25
32
|
|
|
26
33
|
```bash
|
|
27
34
|
npx --prefer-online -y @contextstream/mcp-server@latest setup
|
|
28
35
|
```
|
|
29
36
|
|
|
30
|
-
|
|
37
|
+
That one command detects your AI editors, writes their MCP configs and rules, installs lifecycle hooks where supported, indexes your project in the background, and **verifies everything it just did** — then you restart your editor and your AI has memory. Free tier available.
|
|
38
|
+
|
|
39
|
+
Automating it? Zero-prompt mode takes every default:
|
|
40
|
+
|
|
41
|
+
```bash
|
|
42
|
+
npx --prefer-online -y @contextstream/mcp-server@latest setup --yes
|
|
43
|
+
```
|
|
31
44
|
|
|
32
45
|
<p align="center">
|
|
33
|
-
<img src="compare1.gif" alt="ContextStream
|
|
46
|
+
<img src="compare1.gif" alt="Side-by-side comparison: an AI coding assistant with ContextStream memory and semantic search vs. without" width="700" />
|
|
34
47
|
</p>
|
|
35
48
|
|
|
36
49
|
---
|
|
37
50
|
|
|
38
|
-
##
|
|
51
|
+
## We win on memory benchmarks — measured honestly
|
|
39
52
|
|
|
40
|
-
|
|
53
|
+
**ContextStream scores 90.0% on the full LongMemEval-S benchmark**, the standard test of conversational memory over ~115k-token multi-session histories. That's the complete 500-instance suite with the official GPT-4o judge — 450/500 correct (89.6% single-shot, 90.0% with self-consistency k=3; Wilson 95% CI [87.1%, 92.3%]). Published June 14, 2026.
|
|
41
54
|
|
|
42
|
-
|
|
43
|
-
|
|
44
|
-
|
|
45
|
-
|
|
46
|
-
|
|
47
|
-
irm https://contextstream.io/scripts/mcp.ps1 | iex
|
|
48
|
-
```
|
|
55
|
+
| System | LongMemEval-S | Notes |
|
|
56
|
+
|---|:---:|---|
|
|
57
|
+
| **ContextStream** | **90.0%** | Full 500 instances, official GPT-4o judge |
|
|
58
|
+
| Zep | 90.2% | Vendor-published — a statistical tie (0.2 pt is inside measurement noise) |
|
|
59
|
+
| supermemory | 85.4% | Vendor-published — ContextStream wins with statistical significance |
|
|
49
60
|
|
|
50
|
-
|
|
61
|
+
On **multi-session recall** — the memory that actually matters for a coding agent working across days of sessions — ContextStream scores **81.2% vs Zep's published 57.9%** in the per-family comparison. And on the agentic project-memory benchmark, the same memory raises **agent task success from 58% to 96%**.
|
|
51
62
|
|
|
52
|
-
|
|
53
|
-
contextstream-mcp setup
|
|
54
|
-
```
|
|
63
|
+
Full methodology, per-family breakdowns, and judge-comparability notes (competitor numbers are cited from each vendor's own publications): **[contextstream.io/benchmarks](https://contextstream.io/benchmarks)**
|
|
55
64
|
|
|
56
|
-
|
|
65
|
+
---
|
|
57
66
|
|
|
58
|
-
|
|
59
|
-
npx --prefer-online -y @contextstream/mcp-server@latest setup
|
|
60
|
-
```
|
|
67
|
+
## What is ContextStream?
|
|
61
68
|
|
|
62
|
-
|
|
69
|
+
**ContextStream is a Model Context Protocol (MCP) server that gives AI coding assistants long-term memory and deep codebase understanding.** It indexes your code for semantic search, records your decisions, lessons, and plans across sessions, maps your dependency graph, and pulls in team knowledge from GitHub, Slack, and Notion — then delivers exactly the right slice of all that to your AI on every message.
|
|
63
70
|
|
|
64
|
-
|
|
71
|
+
It works with any MCP client: Claude Code, Cursor, VS Code + GitHub Copilot, Windsurf, Cline, Roo Code, Kilo Code, Codex CLI, OpenCode, Aider, Antigravity, and Claude Desktop.
|
|
65
72
|
|
|
66
73
|
---
|
|
67
74
|
|
|
68
|
-
##
|
|
75
|
+
## Why do AI coding assistants forget everything?
|
|
69
76
|
|
|
70
|
-
|
|
77
|
+
Because every conversation starts from zero. Your AI re-reads the same files, re-derives the same architecture, repeats last week's mistake, and loses the thread the moment the context window compacts. ContextStream fixes the whole class of problem:
|
|
71
78
|
|
|
72
|
-
|
|
73
|
-
|
|
74
|
-
**
|
|
79
|
+
| Without ContextStream | With ContextStream |
|
|
80
|
+
|--------|-------|
|
|
81
|
+
| AI greps files one-by-one, burning tokens | **Semantic code search** finds code by meaning in milliseconds |
|
|
82
|
+
| Context lost when conversations get long | **Pre-compaction capture** saves critical state before it's gone — and restores it after |
|
|
83
|
+
| Same mistakes repeated across sessions | **Lessons system** surfaces past failures *before* your AI repeats them |
|
|
84
|
+
| "Why did we choose X?" — nobody remembers | **Decisions and plans** persist and resurface when relevant |
|
|
85
|
+
| Team knowledge scattered across tools | **GitHub, Slack, and Notion knowledge**, queried automatically |
|
|
86
|
+
| Generic answers with no project awareness | **Workspace context** on every single message |
|
|
75
87
|
|
|
76
88
|
---
|
|
77
89
|
|
|
78
|
-
## What
|
|
90
|
+
## What your AI can do after setup
|
|
79
91
|
|
|
80
|
-
|
|
81
|
-
|
|
82
|
-
| AI searches files one-by-one, burning tokens | **Semantic search** finds code by meaning in milliseconds |
|
|
83
|
-
| Context lost when conversations get long | **Smart compression** preserves what matters before compaction |
|
|
84
|
-
| Team knowledge scattered across tools | **Unified intelligence** from GitHub, Slack, Notion—automatically |
|
|
85
|
-
| Same mistakes repeated across sessions | **Lessons system** ensures your AI learns from every failure |
|
|
86
|
-
| Generic responses, no project awareness | **Deep context** about your architecture, decisions, patterns |
|
|
92
|
+
### 🔍 Find code by meaning, not keywords
|
|
93
|
+
Ask *"where do we handle authentication?"* and get ranked, snippet-level answers instantly. Hybrid semantic + keyword search with exact-token fusion, so a symbol lookup like `resolveWriteScope` lands the definition — not lookalikes. Search works the moment setup finishes: keyword results come back immediately while the semantic index builds in the background.
|
|
87
94
|
|
|
88
|
-
|
|
95
|
+
### 🧠 Remember everything that matters
|
|
96
|
+
Decisions, lessons, preferences, plans, tasks, docs, runbooks — captured during work and surfaced automatically on later turns, in later sessions, even after context compaction. Every prior session's transcript is indexed and queryable: *"what did we decide about the id format last week?"* just works.
|
|
89
97
|
|
|
90
|
-
|
|
98
|
+
### 💬 Ask the workspace when stuck
|
|
99
|
+
The built-in **Agent Q&A** tool lets your AI ask your workspace's knowledge base — prior decisions, conventions, runbooks, guardrails — and get a grounded answer with citations for every claim.
|
|
91
100
|
|
|
92
|
-
###
|
|
93
|
-
|
|
101
|
+
### 🕸️ See the whole graph
|
|
102
|
+
*"What depends on `UserService`?" "What breaks if I change this function?"* Dependency mapping, impact analysis, circular-dependency and dead-code detection over your whole codebase.
|
|
94
103
|
|
|
95
|
-
###
|
|
96
|
-
|
|
104
|
+
### 📦 Hand off context between agents
|
|
105
|
+
**ContextCapsule** packages project state into a portable, shareable snapshot — bootstrap a fresh agent, hand off to a teammate, or share a token-gated link with an external agent.
|
|
97
106
|
|
|
98
|
-
###
|
|
99
|
-
|
|
107
|
+
### 🛡️ Survive long sessions
|
|
108
|
+
Token pressure is tracked continuously (with thresholds sized to your model's context window). Before compaction hits, critical state is checkpointed; after it, context restores.
|
|
100
109
|
|
|
101
|
-
|
|
102
|
-
"What depends on UserService?" "What's the impact of changing this function?" Your AI sees the connections across your entire codebase.
|
|
110
|
+
---
|
|
103
111
|
|
|
104
|
-
|
|
105
|
-
|
|
112
|
+
## Which AI editors and agents does it support?
|
|
113
|
+
|
|
114
|
+
| Editor / Agent | Managed rules | MCP config | Lifecycle hooks |
|
|
115
|
+
|---|:---:|:---:|:---:|
|
|
116
|
+
| Claude Code | ✅ | ✅ | ✅ |
|
|
117
|
+
| Cursor | ✅ (`.cursor/rules/*.mdc`) | ✅ | ✅ |
|
|
118
|
+
| Windsurf | ✅ | ✅ | ✅ |
|
|
119
|
+
| Cline | ✅ | ✅ | ✅ |
|
|
120
|
+
| Roo Code | ✅ | ✅ | ✅ |
|
|
121
|
+
| Kilo Code | ✅ | ✅ | rules-based |
|
|
122
|
+
| VS Code + GitHub Copilot | ✅ | ✅ (incl. hosted OAuth) | rules-based |
|
|
123
|
+
| Codex CLI | ✅ | ✅ | rules-based |
|
|
124
|
+
| OpenCode | ✅ | ✅ | rules-based |
|
|
125
|
+
| Aider | ✅ | ✅ | rules-based |
|
|
126
|
+
| Antigravity | ✅ | ✅ | rules-based |
|
|
127
|
+
| Claude Desktop | — | ✅ | — |
|
|
128
|
+
|
|
129
|
+
Anything that speaks the Model Context Protocol can connect — the table just shows what the setup wizard configures automatically.
|
|
106
130
|
|
|
107
131
|
---
|
|
108
132
|
|
|
109
|
-
## The
|
|
133
|
+
## The tools your AI gets
|
|
134
|
+
|
|
135
|
+
36 tools in the default surface, organized as consolidated domains so they cost ~75% fewer tokens than individual registrations:
|
|
110
136
|
|
|
111
137
|
```
|
|
112
|
-
init
|
|
113
|
-
|
|
114
|
-
|
|
115
|
-
session
|
|
116
|
-
|
|
117
|
-
graph
|
|
118
|
-
|
|
119
|
-
|
|
120
|
-
|
|
138
|
+
init / context → workspace state + the right context on every message
|
|
139
|
+
search → semantic, hybrid, keyword, pattern, exhaustive, refactor modes
|
|
140
|
+
memory → events, decisions, docs, runbooks, tasks, todos, diagrams, transcripts
|
|
141
|
+
session → capture decisions & lessons, recall past sessions, plans, retroactive capture
|
|
142
|
+
qa → grounded Q&A over your workspace knowledge base, with citations
|
|
143
|
+
graph → dependencies, impact analysis, circular deps, unused code
|
|
144
|
+
capsule → portable, shareable context snapshots for agent handoffs
|
|
145
|
+
entity → tickets, incidents, releases, sprints, OKRs, risks
|
|
146
|
+
project / workspace / skill / media / vcs / reminder / integration / help
|
|
121
147
|
```
|
|
122
148
|
|
|
123
|
-
Your AI uses
|
|
149
|
+
Plus focused write tools (`capture_plan`, `memory_create_doc`, …) so agents that display tool names show *what* they're doing. Your AI uses all of this automatically — you just code.
|
|
124
150
|
|
|
125
151
|
---
|
|
126
152
|
|
|
127
|
-
##
|
|
153
|
+
## CLI commands
|
|
128
154
|
|
|
129
|
-
|
|
155
|
+
```bash
|
|
156
|
+
contextstream-mcp setup # interactive onboarding wizard
|
|
157
|
+
contextstream-mcp setup --yes # zero-prompt setup with sane defaults (great for CI/dotfiles)
|
|
158
|
+
contextstream-mcp doctor # ✓/✗ diagnostics: auth, scope, index health, rules, hooks
|
|
159
|
+
contextstream-mcp index [path] # index a project folder on demand
|
|
160
|
+
```
|
|
130
161
|
|
|
131
|
-
|
|
132
|
-
- If no mapping exists, it uses a single hidden global fallback workspace (`.contextstream-global`) in workspace-only mode.
|
|
133
|
-
- Context/memory/session tools continue to work without hard setup errors.
|
|
134
|
-
- Project-bound actions (for example `project(action="ingest_local")`) return guided remediation to create/select a project instead of failing with a raw `project_id required` error.
|
|
135
|
-
- As soon as you enter a mapped project folder, that real workspace/project is prioritized and replaces fallback scope.
|
|
162
|
+
`setup --editors=claude,cursor` limits configuration to specific editors; `doctor` tells you exactly what's misconfigured and how to fix it — it runs automatically at the end of every setup.
|
|
136
163
|
|
|
137
164
|
---
|
|
138
165
|
|
|
139
|
-
## Manual
|
|
166
|
+
## Manual configuration
|
|
140
167
|
|
|
141
168
|
> Skip this if you ran the setup wizard.
|
|
142
169
|
|
|
@@ -215,11 +242,9 @@ For the local variant, export `CONTEXTSTREAM_API_KEY` before launching OpenCode.
|
|
|
215
242
|
</details>
|
|
216
243
|
|
|
217
244
|
<details>
|
|
218
|
-
<summary><b>VS Code</b></summary>
|
|
245
|
+
<summary><b>VS Code + GitHub Copilot</b></summary>
|
|
219
246
|
|
|
220
|
-
|
|
221
|
-
|
|
222
|
-
**Hosted remote MCP (recommended)**
|
|
247
|
+
The easiest path is the hosted remote MCP with built-in OAuth — no API key in the config file:
|
|
223
248
|
|
|
224
249
|
```json
|
|
225
250
|
{
|
|
@@ -232,177 +257,117 @@ For GitHub Copilot in VS Code, the easiest path is the hosted remote MCP with bu
|
|
|
232
257
|
}
|
|
233
258
|
```
|
|
234
259
|
|
|
235
|
-
|
|
236
|
-
|
|
237
|
-
`npx @contextstream/mcp-server@latest setup` now defaults VS Code/Copilot to this hosted remote when you are using the production ContextStream cloud. To force a local runtime instead, run setup with `CONTEXTSTREAM_VSCODE_MCP_MODE=local`.
|
|
238
|
-
|
|
239
|
-
For self-hosted or non-default API deployments, local runtime remains the default:
|
|
240
|
-
|
|
241
|
-
**Rust MCP (recommended)**
|
|
260
|
+
`setup` defaults VS Code/Copilot to this hosted remote on the production cloud. To force a local runtime, run setup with `CONTEXTSTREAM_VSCODE_MCP_MODE=local`, or use stdio directly:
|
|
242
261
|
|
|
243
262
|
```json
|
|
244
263
|
{
|
|
245
264
|
"servers": {
|
|
246
265
|
"contextstream": {
|
|
247
266
|
"type": "stdio",
|
|
248
|
-
"command": "
|
|
249
|
-
"args": [],
|
|
267
|
+
"command": "npx",
|
|
268
|
+
"args": ["--prefer-online", "-y", "@contextstream/mcp-server@latest"],
|
|
250
269
|
"env": {
|
|
251
270
|
"CONTEXTSTREAM_API_URL": "https://api.contextstream.io",
|
|
252
271
|
"CONTEXTSTREAM_API_KEY": "your_key",
|
|
253
|
-
"CONTEXTSTREAM_TOOLSET": "complete"
|
|
254
|
-
"CONTEXTSTREAM_TRANSCRIPTS_ENABLED": "true",
|
|
255
|
-
"CONTEXTSTREAM_HOOK_TRANSCRIPTS_ENABLED": "true",
|
|
256
|
-
"CONTEXTSTREAM_SEARCH_LIMIT": "15",
|
|
257
|
-
"CONTEXTSTREAM_SEARCH_MAX_CHARS": "2400"
|
|
272
|
+
"CONTEXTSTREAM_TOOLSET": "complete"
|
|
258
273
|
}
|
|
259
274
|
}
|
|
260
275
|
}
|
|
261
276
|
}
|
|
262
277
|
```
|
|
263
278
|
|
|
264
|
-
|
|
279
|
+
Keep both `~/.copilot/mcp-config.json` (uses `mcpServers`) and `.vscode/mcp.json` (uses `servers`) in sync — setup writes both.
|
|
280
|
+
|
|
281
|
+
</details>
|
|
282
|
+
|
|
283
|
+
<details>
|
|
284
|
+
<summary><b>GitHub Copilot CLI</b></summary>
|
|
285
|
+
|
|
286
|
+
Use `/mcp add` interactively, or add to `~/.copilot/mcp-config.json`:
|
|
265
287
|
|
|
266
288
|
```json
|
|
267
289
|
{
|
|
268
|
-
"
|
|
290
|
+
"mcpServers": {
|
|
269
291
|
"contextstream": {
|
|
270
|
-
"type": "stdio",
|
|
271
292
|
"command": "npx",
|
|
272
293
|
"args": ["--prefer-online", "-y", "@contextstream/mcp-server@latest"],
|
|
273
294
|
"env": {
|
|
274
295
|
"CONTEXTSTREAM_API_URL": "https://api.contextstream.io",
|
|
275
296
|
"CONTEXTSTREAM_API_KEY": "your_key",
|
|
276
|
-
"CONTEXTSTREAM_TOOLSET": "complete"
|
|
277
|
-
"CONTEXTSTREAM_TRANSCRIPTS_ENABLED": "true",
|
|
278
|
-
"CONTEXTSTREAM_HOOK_TRANSCRIPTS_ENABLED": "true",
|
|
279
|
-
"CONTEXTSTREAM_SEARCH_LIMIT": "15",
|
|
280
|
-
"CONTEXTSTREAM_SEARCH_MAX_CHARS": "2400"
|
|
297
|
+
"CONTEXTSTREAM_TOOLSET": "complete"
|
|
281
298
|
}
|
|
282
299
|
}
|
|
283
300
|
}
|
|
284
301
|
}
|
|
285
302
|
```
|
|
286
303
|
|
|
304
|
+
See the [GitHub Copilot CLI documentation](https://docs.github.com/en/copilot/concepts/agents/about-copilot-cli) for details.
|
|
305
|
+
|
|
287
306
|
</details>
|
|
288
307
|
|
|
289
308
|
<details>
|
|
290
|
-
<summary><b>
|
|
309
|
+
<summary><b>Unmapped folders (global fallback workspace)</b></summary>
|
|
291
310
|
|
|
292
|
-
|
|
311
|
+
Folders that aren't associated with any project (your home directory, ad-hoc scratch dirs) still work: `init` falls back to a hidden catch-all workspace in workspace-only mode, memory/session/context tools keep functioning, and project-bound actions return guided remediation instead of raw errors. The moment you enter a mapped project folder, the real workspace/project takes over.
|
|
293
312
|
|
|
294
|
-
|
|
295
|
-
/mcp add
|
|
296
|
-
```
|
|
313
|
+
</details>
|
|
297
314
|
|
|
298
|
-
|
|
315
|
+
---
|
|
299
316
|
|
|
300
|
-
|
|
317
|
+
## FAQ
|
|
301
318
|
|
|
302
|
-
|
|
303
|
-
{
|
|
304
|
-
"mcpServers": {
|
|
305
|
-
"contextstream": {
|
|
306
|
-
"command": "contextstream-mcp",
|
|
307
|
-
"args": [],
|
|
308
|
-
"env": {
|
|
309
|
-
"CONTEXTSTREAM_API_URL": "https://api.contextstream.io",
|
|
310
|
-
"CONTEXTSTREAM_API_KEY": "your_key",
|
|
311
|
-
"CONTEXTSTREAM_TOOLSET": "complete",
|
|
312
|
-
"CONTEXTSTREAM_TRANSCRIPTS_ENABLED": "true",
|
|
313
|
-
"CONTEXTSTREAM_HOOK_TRANSCRIPTS_ENABLED": "true",
|
|
314
|
-
"CONTEXTSTREAM_SEARCH_LIMIT": "15",
|
|
315
|
-
"CONTEXTSTREAM_SEARCH_MAX_CHARS": "2400"
|
|
316
|
-
}
|
|
317
|
-
}
|
|
318
|
-
}
|
|
319
|
-
}
|
|
320
|
-
```
|
|
319
|
+
### What is an MCP server?
|
|
321
320
|
|
|
322
|
-
|
|
321
|
+
An MCP (Model Context Protocol) server exposes tools and context to AI assistants over a standard protocol. Claude Code, Cursor, VS Code Copilot, Windsurf, and most modern AI coding tools are MCP clients — install one server, and every client you use gets the same capabilities.
|
|
323
322
|
|
|
324
|
-
|
|
325
|
-
{
|
|
326
|
-
"mcpServers": {
|
|
327
|
-
"contextstream": {
|
|
328
|
-
"command": "npx",
|
|
329
|
-
"args": ["--prefer-online", "-y", "@contextstream/mcp-server@latest"],
|
|
330
|
-
"env": {
|
|
331
|
-
"CONTEXTSTREAM_API_URL": "https://api.contextstream.io",
|
|
332
|
-
"CONTEXTSTREAM_API_KEY": "your_key",
|
|
333
|
-
"CONTEXTSTREAM_TOOLSET": "complete",
|
|
334
|
-
"CONTEXTSTREAM_TRANSCRIPTS_ENABLED": "true",
|
|
335
|
-
"CONTEXTSTREAM_HOOK_TRANSCRIPTS_ENABLED": "true",
|
|
336
|
-
"CONTEXTSTREAM_SEARCH_LIMIT": "15",
|
|
337
|
-
"CONTEXTSTREAM_SEARCH_MAX_CHARS": "2400"
|
|
338
|
-
}
|
|
339
|
-
}
|
|
340
|
-
}
|
|
341
|
-
}
|
|
342
|
-
```
|
|
323
|
+
### Does ContextStream work with Claude Code / Cursor / Copilot / Windsurf?
|
|
343
324
|
|
|
344
|
-
|
|
325
|
+
Yes — all of them, plus Cline, Roo Code, Kilo Code, Codex CLI, OpenCode, Aider, Antigravity, and Claude Desktop. The setup wizard configures each editor's MCP config, managed rules, and (where the editor supports them) lifecycle hooks automatically.
|
|
345
326
|
|
|
346
|
-
|
|
327
|
+
### Is my code private?
|
|
347
328
|
|
|
348
|
-
|
|
329
|
+
Your code is private and securely stored, isolated per workspace with no cross-tenant access. You control exclusions with `.contextstream/ignore` (gitignore syntax), and `project(action="purge")` completely de-indexes a project on demand — without touching your captured memory.
|
|
349
330
|
|
|
350
|
-
|
|
331
|
+
### How much does it cost?
|
|
351
332
|
|
|
352
|
-
|
|
353
|
-
- `~/.copilot/mcp-config.json`
|
|
354
|
-
- `.vscode/mcp.json`
|
|
355
|
-
- Rust install: use `contextstream-mcp` as the command.
|
|
356
|
-
- Node install: use `npx --prefer-online -y @contextstream/mcp-server@latest` as the command.
|
|
357
|
-
- Force local VS Code/Copilot setup with `CONTEXTSTREAM_VSCODE_MCP_MODE=local`.
|
|
358
|
-
- Force hosted remote VS Code/Copilot setup with `CONTEXTSTREAM_VSCODE_MCP_MODE=remote`.
|
|
359
|
-
- Use `mcpServers` in Copilot CLI config and `servers` in VS Code config.
|
|
333
|
+
There's a free tier to start with. Larger indexes, the full code graph, and team features are on paid plans: see [pricing](https://contextstream.io/pricing).
|
|
360
334
|
|
|
361
|
-
|
|
335
|
+
### How does ContextStream score on memory benchmarks?
|
|
362
336
|
|
|
363
|
-
-
|
|
364
|
-
- Check `CONTEXTSTREAM_API_URL` and `CONTEXTSTREAM_API_KEY` are set.
|
|
365
|
-
- Remove stale version pins like `@contextstream/mcp-server@0.3.xx`.
|
|
366
|
-
- Restart VS Code/Copilot after config changes.
|
|
337
|
+
90.0% on the full 500-instance LongMemEval-S suite with the official GPT-4o judge (89.6% single-shot) — beating supermemory's published 85.4% with statistical significance and matching Zep's published 90.2% within the confidence interval. On multi-session recall specifically, ContextStream scores 81.2% vs Zep's published 57.9%. Methodology and per-family breakdowns: [contextstream.io/benchmarks](https://contextstream.io/benchmarks).
|
|
367
338
|
|
|
368
|
-
|
|
339
|
+
### How is this different from other AI memory tools?
|
|
369
340
|
|
|
370
|
-
|
|
341
|
+
Most tools store notes. ContextStream combines **memory** (decisions, lessons, plans, session transcripts), **semantic code search** over your indexed codebase, a **dependency/knowledge graph**, **grounded Q&A with citations**, and **team integrations** (GitHub, Slack, Notion) behind one MCP server — and proactively delivers the relevant slice on every message instead of waiting to be asked.
|
|
371
342
|
|
|
372
|
-
|
|
343
|
+
### Can I use it in CI or scripted environments?
|
|
373
344
|
|
|
374
|
-
|
|
345
|
+
Yes: `setup --yes` runs the entire wizard with zero prompts (set `CONTEXTSTREAM_API_KEY` in the environment), `--editors=<list>` scopes it, and `contextstream-mcp doctor` gives scriptable ✓/✗ diagnostics.
|
|
375
346
|
|
|
376
|
-
|
|
377
|
-
{
|
|
378
|
-
"contextstream": {
|
|
379
|
-
"type": "stdio",
|
|
380
|
-
"command": "npx",
|
|
381
|
-
"args": ["-y", "@contextstream/mcp-server@latest"],
|
|
382
|
-
"env": {
|
|
383
|
-
"CONTEXTSTREAM_API_KEY": "your-api-key"
|
|
384
|
-
}
|
|
385
|
-
}
|
|
386
|
-
}
|
|
387
|
-
```
|
|
347
|
+
### Do I have to wait for indexing?
|
|
388
348
|
|
|
389
|
-
|
|
349
|
+
No. Project indexing runs in the background — keyword search works immediately, and semantic results fill in as the index builds. Check progress anytime with `contextstream-mcp doctor`.
|
|
390
350
|
|
|
391
|
-
|
|
351
|
+
### How do I uninstall or disable it?
|
|
392
352
|
|
|
393
|
-
|
|
353
|
+
Remove the `contextstream` entry from your editor's MCP config, and set `CONTEXTSTREAM_HOOK_ENABLED=false` (or re-run setup) to disable hooks. `project(action="forget_local")` unbinds a folder locally without touching server-side data.
|
|
394
354
|
|
|
395
|
-
|
|
355
|
+
---
|
|
396
356
|
|
|
397
|
-
|
|
357
|
+
## Troubleshooting
|
|
358
|
+
|
|
359
|
+
- **Start with `contextstream-mcp doctor`** — it checks auth, API reachability, folder scope, index health, rule files, and hooks, with a fix hint per failure.
|
|
360
|
+
- Remove duplicate ContextStream entries across Workspace/User config scopes.
|
|
361
|
+
- Check `CONTEXTSTREAM_API_URL` and `CONTEXTSTREAM_API_KEY` are set; remove stale version pins like `@contextstream/mcp-server@0.3.xx`.
|
|
362
|
+
- Restart your editor after config changes.
|
|
363
|
+
- **Hosted HTTP OAuth:** the remote transport's OAuth flow routes through `vscode.dev`; where that's blocked (corporate networks), use stdio with an API key instead.
|
|
364
|
+
- **SDK compatibility:** `@modelcontextprotocol/sdk` 1.28.0+ introduces breaking changes; this package pins `>=1.25.1 <1.28.0`. If you see Zod schema errors on startup, check your SDK resolution.
|
|
398
365
|
|
|
399
366
|
---
|
|
400
367
|
|
|
401
368
|
## Links
|
|
402
369
|
|
|
403
|
-
**Website:** https://contextstream.io
|
|
404
|
-
|
|
405
|
-
**Docs:** https://contextstream.io/docs
|
|
370
|
+
**Website:** https://contextstream.io • **Docs:** https://contextstream.io/docs • **Changelog:** [CHANGELOG.md](CHANGELOG.md)
|
|
406
371
|
|
|
407
372
|
---
|
|
408
373
|
|