Player profile
Concord MCP
An MIT-licensed local-first MCP coordination layer for coding agents, with shared presence, file claims, messaging, task memory, handoffs and review packets.
Profile
Where it fits
Concord MCP is a TypeScript stdio MCP server for agents working in one repository. Claude Code, Codex, Cursor, Gemini CLI and other compatible clients can share presence, communicate and identify overlapping file claims before editing.
A repository-local SQLite database records tasks, context, ownership, messages and review evidence. Handoffs and assignments have explicit acceptance states. Concord supplies coordination state around existing agents; it is not an autonomous worker or code reviewer.
Builder web analytics
Measure outcomes from Concord MCP-assisted work
Concord MCP helps coordinate agent work. Separately configured product analytics can show the observed user-facing results of a deployed change.
This is an optional measurement workflow, not a native Concord MCP integration with Agent Analytics. Configure product tracking and authorized analytics access separately; the listing does not install tracking or report agent-run telemetry.
First loop to measure
- a team coordinates and reviews a change to a product surface
- the reviewed change is deployed to a separately instrumented project
- a human or an authorized agent reads observed product outcomes
- the team uses that evidence to select the next task
Copyable prompt
If product tracking and analytics access are already configured, inspect the deployed change over an appropriate observation window. Report measured outcomes, missing evidence and limitations. Do not infer causation from before-and-after movement or treat agent activity as product usage.