ContextStream

io.contextstreamPublished by contextstream.ioOfficial publisherv0.5.35Updated Nov 2, 2026

Persistent memory and cross-session learning for AI coding assistants (hosted remote MCP).

VerifiedStreamable HTTPWeb executableKnowledge & MemoryCommunication & CollaborationMedia & Design

Overview

AI-generated overview

Hosted memory server that lets an AI coding assistant find relevant files, recall saved project decisions, and build on past work across sessions and tools.

What you can do
  • Find files relevant to a change and cite the sources behind them
  • Save project decisions with their reasons and retrieve them in later sessions
  • Index connected code, docs and conversations for hosted search
  • Generate brand images, sounds and product films through a studio tool, with plan, make, status, result and revise steps
  • Draft, preview, test and send email campaigns through the team's own Resend account, and manage contacts and unsubscribes
  • Optionally check packages named in install commands against public registries before they run
When to use it
Useful when an assistant should carry context between sessions and tools, such as recalling why a decision was made or locating the right files in a large codebase. Also relevant for teams that want brand asset generation or email campaigns driven from the same workspace.
Requirements
Remote Streamable HTTP endpoint with OAuth sign-in during onboarding; a free account with 10,000 monthly credits and no credit card. A local npm launcher (Node.js 20+) is an alternative and downloads a native binary. Scripted setup reads CONTEXTSTREAM_API_KEY and may need a workspace ID. Email features require a connected Resend account.
Before you install
Indexing sends eligible source contents to ContextStream for hosted search, and transcript saving plus local Git metadata capture are on by default. Studio make and email send spend credits or send mail and are meant to require your explicit go-ahead; erasing a contact cannot be undone. Review data handling before connecting sensitive projects.

Installation

In SourceWeft

  1. Open ContextStream in the dashboard and add it to a workspace.
  2. Connect the required credentials. They are stored privately and never shown on public pages.
  3. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/io.contextstream%2Fmcp/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config. The client completes OAuth sign-in on first connect.

{
  "mcpServers": {
    "contextstream": {
      "type": "http",
      "url": "https://mcp.contextstream.io/mcp?default_context_mode=fast&src=registry"
    }
  }
}

README

[ContextStream]

ContextStream MCP Server

The context platform for AI agents.

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.

[ContextStream benchmarks: LongMemEval-S 96.8% (484 of 500), LoCoMo 95.7%, code search 98.77% best answer in the top 10, agent tasks 96% (23 of 24, up from 58% without it)]

The numbers, their sources, and what they do not claim are under Benchmarks.

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

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? · 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.

Benchmarks

Each benchmark runs through the production API, is registered before its results are read, and is published with its method, confidence interval, and losses.

BenchmarkContextStreamCompared with
LongMemEval-S, all 500 questions96.8% (484/500); 96.0% on the half held out from tuningAbove Mastra (94.87%) and supermemory (85.4%) on the same official GPT-4o judge. Level with agentmemory's self-reported 96.2%, which is inside our 95% interval
LoCoMo, all 1,540 questions95.7% (1474/1540); 95.8% held out; 97.8% on the audited answer keyAbove every system in the EverMemOS paper's same-judge table: EverMemOS 93.05%, Zep 85.22%, MemOS 80.76%, MemU 66.67%, Mem0 64.20%
Code search, 177 judged developer queries98.77% best answer in the top 10; 100% a useful file in the top 10Embedding-only search 72.84% and ripgrep 42.59% on the same queries and judgments
Agent tasks, 8 tasks × 3 trials23/24 passed (96%); 9/9 on tasks that need team knowledge14/24 (58%) and 0/9 with the repository alone

61 ms median server-side search time (127 ms p95) in the October 27 production run. End to end it was 223 ms, because the client ran in a different region from the one serving the workspace. Your latency depends on your distance from that region.

Competitor figures are as each vendor or the EverMemOS paper published them; we did not re-run them, and readers and judges differ across rows. The code-search baselines come from the August 1 run on the same queries. The agent-task result uses one repository and one agent model, so treat it as directional. Results, methodology, and limitations.

ContextStudio

For people ContextStream Create offers one-prompt making to, the server adds one tool, studio: ask for a film, a product explainer filmed from your connected product, an image, sound or music in plain words, and ContextStudio's producer plans the pieces from what your team knows (brand kit, docs, decisions, connected products). There are no models to pick.

  • Brand work by name. Brand images (social sets in each network's size, ad sets, hero and product shots, posters and flyers with print PDFs, email headers, brand graphics) and brand sounds (sonic logos, music beds, loops, effect packs, voice-overs, podcast intros and outros): pass form, with sizes (up to 6, such as instagram-post or linkedin-post) or a voice, and the plan keeps to it.
  • Plan, then price. plan returns the pieces and one price ("up to N credits, likely about M") and spends nothing. Pass what your agent knows that the workspace may not (the diff it just made, release notes, the doc it has open) as context; the producer reads it next to the team's own context.
  • Your go-ahead. make spends at most the plan's price, and only after you agree: a client that can ask you (MCP elicitation, or a stateless input_required result) asks you itself; otherwise the agent passes the price you accepted.
  • Following it. status reports each piece while it waits (with notifications/progress where the call asks for them); a product film takes 13 to 21 minutes. result shows images inline and links video and sound (signed links valid about 15 minutes), with each piece's placard. Brand work comes as files, each with its own link: every size as PNG, JPG and WebP with a ZIP of the set, a print PDF, or WAV and MP3 for the web with a broadcast master and stems, plus alt text, a caption and the checks it was held to.
  • Revising. revise starts from a made image or sound: a variation (more like it), a revision (it, changed as you say) or a resize (an image in new sizes). Also stop, library, brand and products.
  • Email, where Create offers it. Campaigns sent through your team's own Resend account. email_draft writes one in your brand from a prompt ("announce our winter sale to customers") and sends nothing; email_audiences, email_campaigns, email_test (to your own address or Resend's test addresses), email_cancel and email_report (a campaign's delivery, opens, clicks, bounces and complaints, or the workspace's trends). email_send goes only with your go: the client asks you when it can; otherwise the agent shows you the campaign and its recipient count and passes the count you agreed to. email_preview gives a link to share that shows the email in Gmail, Outlook and Apple Mail mockups (desktop, tablet and phone, light and dark, images on or off), with the inbox line and what to check. email_revise changes a draft from plain words ("shorter subject") or sets its subject and preview line; email_duplicate makes a draft copy. email_contacts lists, adds (with where they agreed to hear from you) or unsubscribes contacts; erasing one can't be undone, so it is the delete tool's (studio.email_contact_erase), after your go; email_unsubscribes shows the suppression list with why and when, and takes an address off it only with your go. Resend is connected in the studio, never through an agent: the tool refuses anything shaped like a Resend key.
  • Connector. The hosted path /studio serves only this tool, for Claude.ai or ChatGPT connectors, with OAuth tokens bound to that resource (read:studio, write:studio).

Data controls

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.

Other installation options and troubleshooting

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 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

bash
contextstream-mcp setup --dry-runcontextstream-mcp doctorcontextstream-mcp doctor --repair

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-stdincontextstream-mcp setup --yes --editors=claude --workspace-id=<UUID> --project-path=.

Package Bouncer (opt-in)

A hook for Claude Code and Cursor that checks the packages an install command names against their public registry before the command runs. It covers npm, pnpm, yarn, bun, npx, pip, uv, uvx, pipx, poetry and cargo, including claude mcp add ... -- npx ....

  • It denies a package the registry does not have, naming the popular package it looks like. An agent may have invented the name, and anyone can register it.
  • It asks before a barely downloaded lookalike of a popular package.
  • It allows everything else, including whenever a lookup fails or takes too long.

It skips projects and commands that use a private registry (.npmrc, pip.conf, uv or poetry sources, --registry, --index-url). CONTEXTSTREAM_PACKAGE_BOUNCER=off turns it off.

Claude Code: add this entry to PreToolUse in ~/.claude/settings.json, next to the hooks setup installed. update-hooks leaves it alone.

json
{ "matcher": "Bash", "hooks": [{ "type": "command", "command": "contextstream-mcp hook package-bouncer", "timeout": 8 }] }

Cursor (~/.cursor/hooks.json):

json
{ "version": 1, "hooks": { "beforeShellExecution": [{ "command": "contextstream-mcp hook package-bouncer" }] } }

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.

bash
cargo build --locked -p mcp-server --bin contextstream-mcpcargo 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

Optional deep project learning

Deep project learning starts off for new accounts. Interactive setup offers it once per account (or once when terms change) and remembers if you decline; plain contextstream-mcp setup --yes preserves your current choice.

bash
contextstream-mcp configure --account-learning status   # show current consent statecontextstream-mcp configure --account-learning on       # open privacy page in browser (or print URL)contextstream-mcp configure --account-learning off      # withdraw consent and queue deletion

--deep-learning is accepted as an alias for --account-learning. Only a person can grant consent by ticking the unchecked box on the signed-in privacy page (https://contextstream.io/dashboard/account/privacy); agents and API keys cannot consent for you. Doctor and init show status only. See data handling and controls.

Source: README.md at commit 0f8ff20

Tools

0
This server asks you to sign in, so SourceWeft could not read its tools without an account and has not indexed them. What a connected account sees can depend on that account and its permissions.

Version history

1
  1. v0.5.35LatestSep 16, 2026

Score

85% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts