ContextStream MCP Server
<!-- mcp-name: io.github.contextstream/mcp-server -->
<p align="center">
<img src="assets/contextstream-logo.png" alt="ContextStream" width="64" />
</p>
<h1 align="center">ContextStream MCP Server</h1>
<p align="center"><strong>Persistent memory. Millisecond code search.</strong></p>
## Your agent knows code. Give it the decisions behind yours.
Connect your code, docs, and conversations so your agents can find the right
files, recall saved decisions, and build on past work across sessions and tools.
<a id="install-in-30-seconds"></a>
## Start free with MCP
**10,000 monthly credits. No credit card required.**
Works with Claude Code, Cursor, Codex, GitHub Copilot, Gemini CLI, Qwen Code,
Kimi Code, Muse Code, ZCode, Zed, and [more MCP clients](docs/clients.md), on
Claude, GPT, Gemini, Kimi, GLM, Qwen, and other models.
Create your account or sign in during MCP onboarding. No separate website signup needed.
**macOS and Linux**
```sh
curl -fsSL https://contextstream.io/scripts/mcp.sh | bash
```
**Windows PowerShell**
```powershell
irm https://contextstream.io/scripts/mcp.ps1 | iex
```
Paste the command into your terminal and follow onboarding to connect your
project and supported editor. Restart your editor after setup.
[What gets installed and indexed?](docs/data-handling.md) ·
[Supported clients](docs/clients.md) ·
[Setup guide](https://contextstream.io/docs/editors/setup) ·
[Prefer to start on the web?](https://contextstream.io/lp/mcp-marketplace?utm_source=github&utm_medium=directory&utm_campaign=mcp_organic_2026q3&utm_content=card_cta)
## Make the next session useful
Ask your connected agent:
> Use ContextStream to find the files relevant to my next change. Cite the
> sources and retrieve any saved project decisions that should guide the work.
Then ask it to save a real decision and its reason. Start a new session and
retrieve that decision without explaining it again. Indexing supplies code
context; it cannot recover every undocumented decision.
## Proof and data controls
**95 ms median code search in our published benchmark.** This is the measured
successful-response median for the disclosed configuration, not a latency guarantee.
[See results, methodology, and limitations](https://contextstream.io/benchmarks).
**Scoped access. Traceable sources. Configurable capture.**
Indexing sends eligible source contents to ContextStream for hosted search.
Transcript saving and local Git metadata capture are on by default and can be
turned off. Review [data handling and controls](docs/data-handling.md) before
connecting sensitive projects.
<details>
<summary><strong>Other installation options and troubleshooting</strong></summary>
### npm (Node.js 20+)
```bash
npx -y @contextstream/mcp-server@latest setup
```
The npm launcher downloads the native Rust binary for your platform and verifies
its SHA-256 checksum. Pin an exact package version for production automation.
### Hosted MCP without a local process
For clients supporting Streamable HTTP and OAuth, the hosted endpoint is:
```text
https://mcp.contextstream.io/mcp?default_context_mode=fast
```
[Supported clients](docs/clients.md) lists one-line add commands for Claude
Code, Codex, Gemini CLI, Qwen Code, Copilot CLI, and Droid, and one-click
install for VS Code. Use the [MCP documentation](https://contextstream.io/docs/mcp)
for other clients and stdio alternatives. A hosted connection alone does not
sync your local checkout.
### Preview or diagnose setup
```bash
contextstream-mcp setup --dry-run
contextstream-mcp doctor --scope=all --only-configured
```
### Scripted and CI setup
For automation, wrap the install in `pipefail` so it fails when the download
fails, instead of reporting success after installing nothing:
```bash
bash -o pipefail -c 'curl -fsSL https://contextstream.io/scripts/mcp.sh | bash'
```
`setup --yes` reads the key from `CONTEXTSTREAM_API_KEY` or saved credentials,
and needs `--workspace-id` when the account has more than one workspace:
```bash
export CONTEXTSTREAM_API_KEY=... # or: printf %s "$KEY" | contextstream-mcp configure --api-key-stdin
contextstream-mcp setup --yes --editors=claude --workspace-id=<UUID> --project-path=.
```
</details>
## Open source and contributing
This repository contains the MIT-licensed Rust MCP server, client, editor setup,
and release tooling. The hosted backend is separate and is not included here.
See the [architecture](docs/architecture.md), [release integrity](docs/release.md),
and [latest release](https://github.com/contextstream/mcp-server/releases/latest).
```bash
cargo build --locked -p mcp-server --bin contextstream-mcp
cargo test --locked --workspace
```
Use the pinned Rust toolchain. For contribution checks and commit sign-off, read
[CONTRIBUTING.md](CONTRIBUTING.md). Report vulnerabilities using
[SECURITY.md](SECURITY.md). See [LICENSE](LICENSE), [NOTICE](NOTICE), and
[GOVERNANCE.md](GOVERNANCE.md) for licensing, trademarks, and project governance.
---
**Let humans be human.**
[Docs](https://contextstream.io/docs/mcp) ·
[Pricing](https://contextstream.io/pricing) ·
[Integrations](https://contextstream.io/integrations) ·
[Benchmarks](https://contextstream.io/benchmarks)
TDQS
Scored across 36 tools
Numerous tools have overlapping purposes, such as multiple memory shortcuts (memory_create_doc, memory_update_doc, etc.) and separate session capture tools (session_capture, session_remember) that duplicate session actions. The context and init tools also share similar goals, making it difficult for an agent to select the correct tool.
Tool names are a mix of single words (context, init), verb_noun (capture_plan, generate_editor_rules), and noun_verb patterns (memory_create_doc, session_capture_lesson). There is no consistent naming convention, which reduces predictability.
With 36 tools, the server is on the heavy side. While many features are covered, several tools are redundant shortcuts (e.g., memory_*). Trimming duplicates would improve focus without sacrificing functionality.
The server covers a wide range of operations: memory management, context retrieval, project management, version control, media processing, and integrations. Minor gaps exist (e.g., no explicit code search outside of context), but overall the surface is comprehensive.