presence-mcp
About
PyPI launcher that exposes the presence Claude Code plugin's living project model and outcome telemetry as MCP resources for Claude Desktop, Cursor, and Continue.
Details
- Author
- sara-star-quant
- Categories
- AI, Project Management, Productivity
Jump to
Setup
Install presence-mcp in your MCP client (Claude Desktop, Cursor, Windsurf, and others).
Repository: https://github.com/sara-star-quant/presence-mcp
Follow the installation instructions in the repository README, then restart your MCP client.
PyPI launcher that exposespresence's living project model and outcome telemetry as MCP resources for Claude Desktop, Cursor, Continue, and other MCP-aware clients.
presenceis a Claude Code plugin. It already ships a stdio MCP server atlib/cli.py mcpand exposes two read-only resources per repository (seeWhat you get). This package is the PyPI shim that lets that server be listed in the officialMCP Registryand invoked with a single command name in every per-client config, instead of an absolute path that varies per machine.
The launcher itself speaks no MCP. It locates a local presence install and forwards stdio topython lib/cli.py mcp. About 40 lines of Python, stdlib only.
Then point any MCP client at thepresence-mcpcommand. For Claude Desktop, that's:
{ "mcpServers": { "presence": { "command": "presence-mcp" } } }
Full per-client config forCursorandContinuebelow. Requires Python 3.12+ and a localpresenceinstall.
Two read-only MCP resources, one per repository you've worked on:
<repo_id>is a 12-char SHA-256 prefix of the repo. The server resolves the current repo from the launcher's working directory; seeWorking-directory caveat. Resource schema and protocol details:presence'sdocs/mcp.md.
The samepresence-mcpcommand works in every client.
~/Library/Application Support/Claude/claude_desktop_config.json(macOS), or the equivalent on Windows / Linux:
{ "mcpServers": { "presence": { "command": "presence-mcp" } } }
.cursor/mcp.jsonin the project root, or the global Cursor MCP settings:
{ "mcpServers": { "presence": { "command": "presence-mcp" } } }
{ "mcpServers": [ { "name": "presence", "command": "presence-mcp" } ] }
The launcher accepts JSON-RPC on stdin. Pasting{"jsonrpc":"2.0","id":1,"method":"initialize"}and pressing Enter should yield aninitializeresponse. You can also invoke it aspython -m presence_mcpif a console script isn't convenient.
Ifpresence-mcpreports it could not locate presence, install presence at the standard Claude Code plugin path, or setPRESENCE_MCP_CLI.
presence's MCP server resolves the current repo from the launcher's working directory viagit rev-parse --show-toplevel. MCP clients that launch the server from a fixed directory will only see one repo. To switch repos, either launch a separate instance per project (setcwdin the client's per-server config), or restart the server from the target project root.
- Python:3.12 or newer. CI matrix covers 3.12 / 3.13 / 3.14.
- presence:tested with>= 0.6.0. Older versions back to v0.4.1 (where the MCP server first shipped) may still work but are not exercised by CI.
- Platforms:Linux and macOS exercised in CI. Windows is untested in v0.1.0. The launcher usessubprocess.runwhich is cross-platform, but the default presence install path (~/.claude/plugins/presence/lib/cli.py) needs a real Windows install to confirm. Report issues if you try it.
This launcher is protocol-agnostic: it doesnotrev when presence ships new MCP resources. It only revs when its own resolution logic, CLI surface, orserver.jsoncontent changes.
- Launcher bugs(path detection, install errors, CLI argument forwarding):issues on this repo.
- Resource-content bugs(whatpresence://*/modelreturns, telemetry schema, working-directory behavior, anything about the protocol itself):issues on the presence repo.
presence's MCP server advertisesserverInfo.name = "presence-mcp"in itsinitializeresponse. That's the server's MCP identity. This package is the PyPI launcher. The names match by intent.
- PyPI:https://pypi.org/project/presence-mcp/
- MCP Registry:https://registry.modelcontextprotocol.io/v0/servers?search=presence-mcp(io.github.sara-star-quant/presence-mcp)
- Upstream (presence):https://github.com/sara-star-quant/presence
A project management and session memory tool for AI agents to track projects, tasks, and context during chat sessions.
Local-first deterministic project memory for AI agents: context packs, decisions, gates, risks, claims ledger and explicit checkpoints in project-owned files.
Save your AI chat's working state and load it in any other model, client or provider. Verified on save, secrets stripped.
Persistent AI memory across tools — remember your preferences, code standards, and decisions across Claude Code, Cursor, Codex, and any MCP tool. Local-first, zero-cloud.
A local MCP continuity engine that helps Claude Code pick up the thread across sessions.
One memory URL. Every AI tool. Your rules, lessons, and context — recalled automatically, every conversation.
Portable knowledge layer about you, connected to AI tools via MCP. Learns from how you work. Travels across Claude, ChatGPT, Cursor, and more.
Gives your AI persistent context across every chat and session, so it always knows where your projects stand and what's next.
Interact with task, doc, and project data in Dart, an AI-native project management tool
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
