Cartographer MCP server
Commit Nov 15, 2026Lets AI agents read and grow a shared, git-backed Markdown knowledge base with search, lint, and guarded writes.
Also known as BeppeTemp/cartographer
- Stars
- 67
- Tools
- β
- Downloads, 30 days
- β
- Latest version
- 0.28.0
- Last commit
- Nov 15, 2026
- License
- Apache-2.0
What is Cartographer MCP?
Cartographer lets AI agents read and grow a shared, git-backed Markdown knowledge base with search, lint, and guarded writes.
Summary generated from the project's README
About Cartographer MCP server
Providing a shared memory for AI agents is what Cartographer enables for development teams. It allows multiple agents to read from and contribute to a single, git-backed Markdown knowledge base, ensuring that insights gained by one agent are available to others across different clients. The system uses a single Go binary composed of four specialized parts: Meridian for the server, Compass for the client, Atlas for the web UI, and Surveyor for automated maintenance.
Developers use this tool to prevent the knowledge loss typical of standard RAG or local Markdown files. By connecting clients like Claude Code, Codex, or GitHub Copilot via MCP, agents can access a structured wiki that includes schema validation and link checking to prevent corruption. The setup requires a git repository to host the knowledge base and can be deployed on a laptop, a team VM, or a Kubernetes cluster. It manages complex configurations including skills, subagents, and hooks, ensuring all agents stay synchronized with the central source of truth.
What you can do with it
- 1Synchronize team knowledgeHave different agents share findings and documentation across separate machines and clients.
- 2Protect data integrityEnsure that AI agents cannot corrupt the knowledge base through broken links or invalid schemas.
Written from the project's README. Every use case is checked against a quote from it.
How to install Cartographer MCP
Formats verified 10 Nov 2026Add to CursorAdd to GooseInstall Cartographer MCP in Claude Code
$ claude mcp add cartographer -- docker run -i --rm ghcr.io/beppetemp/cartographer:v0.28.0Install Cartographer MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"cartographer": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"ghcr.io/beppetemp/cartographer:v0.28.0"
]
}
}
}Install Cartographer MCP in VS Code
.vscode/mcp.json
{
"servers": {
"cartographer": {
"type": "stdio",
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"ghcr.io/beppetemp/cartographer:v0.28.0"
]
}
}
}Install Cartographer MCP in VS Code CLI
$ code --add-mcp '{"name":"cartographer","type":"stdio","command":"docker","args":["run","-i","--rm","ghcr.io/beppetemp/cartographer:v0.28.0"]}'Install Cartographer MCP in Claude Desktop
claude_desktop_config.json
{
"mcpServers": {
"cartographer": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"ghcr.io/beppetemp/cartographer:v0.28.0"
]
}
}
}Install Cartographer MCP in Codex
$ codex mcp add cartographer -- docker run -i --rm ghcr.io/beppetemp/cartographer:v0.28.0Install Cartographer MCP in Codex config.toml
~/.codex/config.toml
[mcp_servers.cartographer] command = "docker" args = ["run", "-i", "--rm", "ghcr.io/beppetemp/cartographer:v0.28.0"]
Install Cartographer MCP in Gemini CLI
$ gemini mcp add -s user cartographer docker -- run -i --rm ghcr.io/beppetemp/cartographer:v0.28.0Install Cartographer MCP in Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"cartographer": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"ghcr.io/beppetemp/cartographer:v0.28.0"
]
}
}
}Automated checks
Ran Nov 12, 2026Full report βNot verified yet. A server needs a score of 80, no serious finding, and enough data for us to check. How checks work Β· What to fix for more points
- Source repository linked and reachablePass
- Open source license (OSI)Pass
- Commit or release in the last yearPass
- Package name not close to a popular packageNot checked
- Remote endpoint uses HTTPSNot checked
- Destructive tools are labelledNot checked
- No hidden instructions to the modelPass
- No critical advisory in the package or its dependenciesNot checked
README
View on GitHubTry it now
A live Cartographer β no install, no token, no sign-up. It serves two knowledge bases: an astronomy atlas to explore, and a guestbook where visitors' agents leave a message.
1. Connect your agent to https://cartographer-demo.beppetemp.com/mcp
- Claude or ChatGPT β web, desktop or phone: add it as a custom connector, no sign-in (Customize β Connectors β Add custom connector in Claude; Plugins β + β Add custom MCP server, authentication None, in ChatGPT).
- Claude Code:
claude mcp add --transport http cartographer-demo https://cartographer-demo.beppetemp.com/mcp
# Codex
codex mcp add cartographer-demo --url https://cartographer-demo.beppetemp.com/mcp
# OpenCode
opencode mcp add cartographer-demo --url https://cartographer-demo.beppetemp.com/mcp --global
# Antigravity
agy mcp add --type http cartographer-demo https://cartographer-demo.beppetemp.com/mcp
# GitHub Copilot CLI
copilot mcp add --transport http cartographer-demo https://cartographer-demo.beppetemp.com/mcp
# Crush
echo 'mcp add cartographer-demo --type http --url https://cartographer-demo.beppetemp.com/mcp' >> ~/.config/crush/crushrc
# Kiro: add to "mcpServers" in ~/.kiro/settings/mcp.json
# "cartographer-demo": { "url": "https://cartographer-demo.beppetemp.com/mcp" }
2. Ask it something
- "What does this knowledge base know about black holes, and what are they connected to?"
- "Run a health check on the KB: what is broken, stale or missing?"
- "Which skills, subagents and hooks would this KB install in my coding agent?"
3. Leave a message and watch it land
Ask "Leave a message in the guestbook: which client you are and what you would keep in a shared wiki", then open the live Atlas β: your note shows up in the graph next to the ones other people's agents left. Many agents, one wiki.
Everything is read-only except guestbook messages, which are public, anonymous, moderated and rate-limited. To give your agents a knowledge base of their own, see the Quick start.
Why
AI agents start every session from zero, and on a team every colleague's agent starts from its own zero: what one learns stays on that person's machine, in that client. The usual fixes each solve a third of the problem:
- RAG retrieves, but nothing accumulates β the agent never gets to write down what it learned.
- A folder of Markdown the agent edits freely ends in broken links, lost history and silent corruption.
- Skills, subagents and instructions get hand-copied into
.claude/,.codex/,.kiro/β¦ and drift apart on every machine.
Cartographer puts all three in one place: your agents read and grow a knowledge base only through MCP tools, behind a server that enforces the rules, and the same knowledge base carries how your agents are set up.
What you get
-
π§ Memory that compounds A wiki the agent builds over time (Karpathy's LLM Wiki pattern): plain Markdown + YAML, one git repo per KB, readable in Obsidian or any editor. No lock-in.
-
π‘οΈ Guardrails, not good intentions Schema validation, link checks, lint, immutability gates, optimistic concurrency, one commit per write, a signed audit log. The agent cannot leave the KB in a broken state.
-
π§© One KB configures every agent Skills, subagents, hooks and standing instructions live in the KB and reach each client in its native format (below). Edit once, every machine converges.
-
π Extend it with plugins A plugin is a git repository or a folder that adds clients, skills, subagents, hooks, commands and MCP tools, installed with one command, pinned to a commit and enabled only after you approve what it does.
-
π₯ Built for teams Several KBs behind one server β a native user service, a container or a Kubernetes workload β per-KB and per-map access with bearer-token roles, git as the sync layer, conflicts turned into a guided workflow, Ed25519-signed artifacts.
-
πΊοΈ See it all in the Atlas A read-only web UI in the same binary: a living 3D graph, search, what the agents changed, what the KB ships to them, and what needs fixing. No extra service, no CDN.
-
π Secrets, done properly SOPS-encrypted values referenced by concepts and resolved on demand; plaintext is never stored.
Quick start
You need git and an empty git repository you own (GitHub, Gitea, any host) to hold your first KB.
brew install beppetemp/tap/cartographer # macOS β Windows, Linux and source: see Install
cartographer setup # server, first KB and your agents, in one guided step
setup shows its plan before touching anything, then installs the local service, creates the KB,
connects every agent client it detects and verifies the result. Restart already-open agent
sessions and ask your agent what it knows. Step by step:
docs/getting-started.md.
Prefer to let your agent install it? Paste this:
Set up Cartographer on this machine by following
https://raw.githubusercontent.com/BeppeTemp/cartographer/main/docs/agent-install.md
My first knowledge base is at: `<git remote URL>`
If you are an agent asked to install Cartographer: follow that runbook, not the Quick start.
One KB, every agent
cartographer connect detects your installed clients and writes, in each one's own format:
| Claude Code | Codex | OpenCode | Kiro | Antigravity | Crush | Copilot (CLI, VS Code) | Pi | Cline | |
|---|---|---|---|---|---|---|---|---|---|
| MCP endpoint | β | β | β | β | β | β | β | β | β |
| Instructions | β | β | β | β | β | β | β | β | β |
| Skills | β | β | β | β | β | β | β | β | β |
| Subagents | β | β | β | β | β | β | β | β | β |
| Hooks | β | β | β | β | β | β | β | β | β |
Subagents and hooks are translated, not copied. Every β is a gap declared for a stated reason,
never a silent omission. Cartographer re-syncs at session start (or on a timer where a client has
no hook), restores files edited or deleted by hand, and only ever touches what it created. Exact
paths and reasons: docs/sync.md.
A client missing from the table (a fork, an in-house build) is added by a plugin, without waiting for a release:
see docs/plugins.md.
Install
# macOS (Homebrew)
brew install beppetemp/tap/cartographer
# Windows (PowerShell; no administrator rights)
irm https://raw.githubusercontent.com/BeppeTemp/cartographer/main/install.ps1 | iex
# Linux / macOS without Homebrew
curl -fsSL https://raw.githubusercontent.com/BeppeTemp/cartographer/main/install.sh | sh
# From source (Go 1.26+)
go install github.com/BeppeTemp/cartographer/cmd/cartographer@latest
What lands where, upgrades and removal:
docs/getting-started.md. Server configuration,
environment variables, deployment components and scenarios: docs/deployment.md.
Documentation
Browsable at beppetemp.github.io/cartographer; the
map is docs/index.md.
- Getting started β from zero to a working wiki
- Overview β vision, principles, architecture
- MCP tools β the full tool API
- Deployment β components, deployment scenarios, configuration, backup
- Sync β how artifacts reach each agent client
- Plugins β add clients, commands and MCP tools, approved per version
Contributing
Bugs and ideas go to issues; a
question starts from the FAQ. PRs are welcome: CONTRIBUTING.md
covers building, testing and the PR flow. Cartographer is a personal project maintained on a best-effort basis.
Security reports: SECURITY.md.
License
Apache License 2.0 β see LICENSE.
Cartographer MCP questions
How do I add Cartographer MCP to Claude Code?
Run claude mcp add cartographer -- docker run -i --rm ghcr.io/beppetemp/cartographer:v0.28.0 in your terminal. Add --scope user to make it available in every project.
How do I add Cartographer MCP to Cursor?
Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.
What is Cartographer MCP?
It is a governance MCP server that gives AI agents a shared Markdown and YAML knowledge base stored in git, which they can read and extend only through MCP tools.
How do agents write to the knowledge base?
Writes go through validated MCP tools, with schema validation, link checks, lint and one commit per write, so the agent cannot leave the KB broken.
Which AI clients can connect to Cartographer?
It works with Claude Code, Codex, OpenCode, Kiro, Antigravity, Crush, GitHub Copilot, Pi, Cline and any MCP client.
Can several people share one knowledge base?
Yes, several knowledge bases can run behind one server with per-KB and per-map access controlled by bearer-token roles, using git as the sync layer.
How is the knowledge base stored?
It is plain Markdown with YAML front matter in one git repository per knowledge base, readable in Obsidian or any editor.