MCP Server

Active

MIT

ContextStream MCP Server MCP Server

io.github.contextstreamio/mcp-server

Persistent memory and millisecond code search for AI agents across sessions.

What is the ContextStream MCP Server MCP server?

The ContextStream MCP Server provides persistent memory, code search, and decision tracking for AI agents working with code. It indexes your codebase for fast retrieval, stores project decisions across sessions, and integrates with Claude, Cursor, GitHub Copilot, and other MCP clients.

ContextStream connects your code, documentation, and conversations to give AI agents fast access to relevant files and saved decisions. It offers 95ms median code search, persistent memory for project decisions, and works with major AI editors and models. The service includes 10,000 free monthly credits and supports both local and hosted deployment.

How to install ContextStream MCP Server

Copy-paste configuration for popular MCP clients.

transport: stdio

Config generated by PluginBench — verify against the source before use.

Environment / auth

CONTEXTSTREAM_API_KEY
required
secret
ContextStream API key (create one at contextstream.io)
CONTEXTSTREAM_API_URL
API base URL

~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "@contextstream/mcp-server"
      ],
      "env": {
        "CONTEXTSTREAM_API_KEY": "<YOUR_CONTEXTSTREAM_API_KEY>",
        "CONTEXTSTREAM_API_URL": "<YOUR_CONTEXTSTREAM_API_URL>"
      }
    }
  }
}

Tools & capabilities

Tools this server exposes to the agent.

Code Search — Fast indexed search across your codebase with 95ms median response time
Persistent Memory — Save and retrieve project decisions and context across sessions
Project Context Indexing — Automatic indexing of source code and documentation for agent access
Git Metadata Capture — Local Git metadata capture for decision tracking and source attribution

Use cases

Find relevant files and retrieve saved project decisions before starting a new coding task
Save architectural decisions and design rationale for future reference without re-explaining
Give AI agents fast access to code context across multiple sessions and tools
Track and retrieve undocumented project decisions that guide implementation work
Maintain continuity of AI-assisted work across different editors and coding sessions

ContextStream MCP Server MCP server FAQ

What is ContextStream MCP Server?

ContextStream is an MCP server that provides persistent memory and fast code search for AI agents. It indexes your codebase, stores project decisions, and makes them available across sessions and tools.

Is ContextStream free?

Yes, it starts free with 10,000 monthly credits and no credit card required. Paid plans are available for higher usage.

How do I install it in Cursor or Claude?

Run the one-line installer: `curl -fsSL https://contextstream.io/scripts/mcp.sh | bash` on macOS/Linux or the PowerShell equivalent on Windows. Follow the onboarding to connect your project.

What data does ContextStream collect?

Source code contents are sent to ContextStream for hosted search indexing. Transcript saving and Git metadata capture are on by default but can be disabled. Review the data handling documentation before connecting sensitive projects.

Which editors and AI models does it support?

Works with Claude Code, Cursor, GitHub Copilot, Gemini CLI, Qwen Code, Kimi Code, and other MCP clients on Claude, GPT, Gemini, Kimi, and other models.

Do I need authentication?

Yes, you create an account or sign in during MCP onboarding. An API key is generated automatically; no separate website signup is needed.

README (reference)

Source of truth, from the repository.

<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.

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, 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

curl -fsSL https://contextstream.io/scripts/mcp.sh | bash

Windows 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? · Supported clients · Setup guide · Prefer to start on the web?

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.

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 before connecting sensitive projects.

<details> <summary><strong>Other installation options and troubleshooting</strong></summary>

npm (Node.js 20+)

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:

https://mcp.contextstream.io/mcp?default_context_mode=fast

Supported clients 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 for other clients and stdio alternatives. A hosted connection alone does not sync your local checkout.

Preview or diagnose setup

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 -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:

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, release integrity, and latest release.

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. Report vulnerabilities using SECURITY.md. See LICENSE, NOTICE, and GOVERNANCE.md for licensing, trademarks, and project governance.

Let humans be human.

Docs · Pricing · Integrations · Benchmarks

Related MCP servers

ContinueWith

Maintained

Install the ContinueWith AI handoff widget from coding agents (Cursor, Claude Code, Codex).

JavaScript

View repository →

ConvergeQA Compare (Due Diligence)

Maintained

Compare one prompt across a multi-model panel side by side, with public verification receipts.

Python

MIT

View repository →

ConvergeQA Reviews (Critique & Iterate)

Maintained

Multi-model Critique and Iterate document reviews with public verification receipts.

Python

MIT

View repository →

ResearchSprint

AI research reports: market analysis, competitor intel, blog posts. USDC payment.

Conversor IAE-CNAE

Active

The first fiscal MCP server for Spain: IAE/CNAE 2025, AEAT modelos, IRPF/IVA, RETA quota.

MIT

View repository →

io.github.coo-quack/calc-mcp

Active

21 deterministic tools for math, randomness, dates, encoding, hashing—things AI gets wrong.

TypeScript

MIT

View repository →