mcpField
P
ProjectKeeper

ProjectKeeper

Local
github.comMemory & Knowledge
RepositoryVisit website

About ProjectKeeper

ProjectKeeper maps a project's requests, decisions, plans and completed work for teams handing work between AI agents. It reads existing project materials and provides context packs, while keeping project data on the machine.

Key features

  1. 01Maps requests, plans and delivered work
  2. 02Links decisions to source sessions
  3. 03Tracks earlier plan outcomes
  4. 04Flags gaps and pending decisions
  5. 05Generates agent context packs

Use cases

  1. 01Handing a half-finished project to another agent
  2. 02Checking whether delivered code matches requirements
  3. 03Reviewing the source of a project decision

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "feiyanglyy-stack-projectkeeper": {
      "command": "npx",
      "args": [
        "-y",
        "projectkeeper"
      ]
    }
  }
}
Run commandnpx -y projectkeeper

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npmprojectkeeper1.0.0

Tools

5

Saved tool list · updated 2w ago

ParameterTypeRequiredDescription
cwdstringNoA folder inside the project. Default: the folder the server was started in.
kindenumNoWhat the pack is for. Default: Implement.Implement | Review | Plan | Discuss product | Investigate
portintegerNoWorkbench port. Default: the one in ProjectKeeper's settings (4870).
workstringNoA work item or area, by id or name. Omit for the whole project.
sincestringNoTime of your last pack; gives only what changed since.
projectstringNoProject id (`pk projects` lists them). Default: the project containing cwd.
purposeenumNoStart (default for the project) or Work (default with work).Start | Work
recipientstringNoWho reads it: "Incoming agent" (default) or a role the project recognises.

Details

The maintainer has not added details yet. Check the README in the repository.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.