mcpField
I
issuewatcher

issuewatcher

Local
github.com/mac146Version Control2Updated 3d ago
Repository

About issuewatcher

Ranks new GitHub issues for your AI assistant: what to pick up, what may break your projects

Configuration

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

mcp.json · Universal config
{
  "mcpServers": {
    "mac146-issuewatcher": {
      "command": "npx",
      "args": [
        "-y",
        "issuewatcher-mcp"
      ],
      "env": {
        "GITHUB_TOKEN": "<GITHUB_TOKEN>",
        "SCORING_MODE": "<SCORING_MODE>"
      }
    }
  }
}
Run commandnpx -y issuewatcher-mcp
Environment variables to set
GITHUB_TOKENSecretA GitHub personal access token with read-only access. Create one at https://github.com/settings/personal-access-tokens/new
SCORING_MODEcontributor (issues you could pick up), consumer (issues that may break your projects) or both.

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
npmissuewatcher-mcp0.2.5

Tools

3

Saved tool list · updated 4d ago

ParameterTypeRequiredDescription
modeenumNocontributor: what could I pick up and fix (good first issues, unassigned, fresh). consumer: what could break my projects (issues in libraries I depend on). both: a mix of the two.contributor | consumer | both
limitintegerNoHow many issues to return (1-25).
reposarrayNoOptional: only these repos, each as owner/name.
sincestringNoHow far back to look, as a number plus h or d, for example 24h, 3d or 7d. Maximum 30d.
sourceenumNoWhich watched repos to look at: repos the user starred, source repos of libraries their projects use, or both.starred | dependencies | both
min_scoreintegerNoOnly return issues scoring at least this (0-100).

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.