FairMind Project Context

ai.fairmindPublished by fairmind.aiOfficial publisherv1.0.1Updated Oct 24, 2026

Project memory for coding agents: requirements, decisions, code graph and delivery telemetry.

Overview

AI-generated overview

Hosted FairMind MCP server that gives coding agents project memory: requirements, decisions, code graph and delivery telemetry.

What you can do
  • Read and create needs, user stories, tasks, test cases and requirements in FairMind Studio, and record implementation progress
  • Search, read and record team decisions, requirements and issues, and follow how they changed
  • Search, read and navigate ingested repositories and assess a repository's readiness for AI-assisted development
  • Work with projects, work sessions, attachments and retrieval over project documents
  • Record and read agent activity, audits and decisions
When to use it
Useful when a coding agent should work from a team's existing requirements, recorded decisions and ingested code rather than starting cold, and when its work should be logged so the next session continues from there. Suited to teams already using the FairMind platform.
Requirements
Remote Streamable HTTP endpoint at project-context.fairmind.ai. Requires a FairMind account and a per-organization token sent as an Authorization bearer header; tokens are obtained by contacting FairMind. Any MCP client supporting Streamable HTTP and custom headers works.
Before you install
The token is described as a password: it grants access to the organization's project data, so keep it out of committed files. The server can create Studio items and record decisions and agent activity, which writes data into the organization's workspace. Project data is sent to FairMind's hosted service.

Installation

In SourceWeft

  1. Open FairMind Project Context in the dashboard and add it to a workspace.
  2. Connect Authorization token 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/ai.fairmind%2Fproject-context/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.

{
  "mcpServers": {
    "fairmind-project-context": {
      "type": "http",
      "url": "https://project-context.fairmind.ai/mcp/mcp",
      "headers": {
        "Authorization": "Bearer <YOUR_TOKEN>"
      }
    }
  }
}

README

FairMind Project Context MCP server

Project memory for coding agents: requirements, decisions, code graph and delivery telemetry.

FairMind Project Context is the hosted MCP server of the FairMind platform. It gives a coding agent the context of the project it is working on: the needs, user stories, tasks and tests planned in FairMind Studio, the decisions the team has recorded, and search over the code and documents ingested into FairMind. The agent can also record what it did, so the next session starts from there.

This repository holds the server's registry manifest and its connection instructions. The service is hosted and operated by FairMind; its source code is not published here.

Endpoint

Registry nameai.fairmind/project-context
TransportStreamable HTTP
URLhttps://project-context.fairmind.ai/mcp/mcp
AuthenticationAuthorization: Bearer <FairMind token>

Getting a token

The server requires a FairMind account. Tokens are issued per organization by FairMind: contact us through fairmind.ai to get one.

Treat the token as a password. It gives access to your organization's project data, so keep it out of files you commit.

Connecting

VS Code (GitHub Copilot)

Add this to .vscode/mcp.json. VS Code asks for the token the first time the server starts and stores it securely.

json
{  "inputs": [    {      "type": "promptString",      "id": "fairmind-token",      "description": "FairMind token",      "password": true    }  ],  "servers": {    "fairmind": {      "type": "http",      "url": "https://project-context.fairmind.ai/mcp/mcp",      "headers": {        "Authorization": "Bearer ${input:fairmind-token}"      }    }  }}

Claude Code

bash
claude mcp add --transport http Fairmind https://project-context.fairmind.ai/mcp/mcp \  --header "Authorization: Bearer <your FairMind token>"

Other clients

Any MCP client that supports Streamable HTTP and custom request headers can connect: use the URL above and send the token in the Authorization header.

Tools

The tools are grouped by prefix:

GroupWhat it covers
Studio_*Needs, user stories, tasks, test cases and requirements planned in FairMind Studio; creating them and recording implementation progress
Brain_*The decisions, requirements and issues your team has recorded: search, read, record new ones and follow how they changed over time
Code_*Search, read and navigate the repositories ingested into FairMind, and assess a repository's readiness for AI-assisted development
General_*Projects, work sessions, attachments and retrieval over project documents
Insights_*Recording and reading agent activity, audits and decisions

Support

Contact FairMind through fairmind.ai.

License

The contents of this repository, the manifest and this documentation, are released under the MIT License. The FairMind service itself is proprietary and provided under your agreement with FairMind.

Source: README.md at commit 5609b34

Tools

0
This server asks for a credential such as an API key, so SourceWeft could not read its tools without one and has not indexed them.

Version history

2
  1. v1.0.1LatestSep 17, 2026
  2. v1.0.0Sep 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