An MCP server configuration for Pluck, a repository tool launched against the current project directory.

Use it when a project needs to start or configure the Pluck MCP server for repository operations.

It lets an agent connect Pluck to the repository it is working on through the configured command and repository path.

pluck — MCP server by hunhee98

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods

npx agentmods add mcp/hunhee98/pluck/claude-code-pluck

Clone the repo

git clone --depth 1 https://github.com/hunhee98/pluck

Made for: Claude Code, Codex, Cursor, Gemini CLI, OpenCode.

Per session not measured What this adds to a session before it is invoked.

When invoked not measured Not applicable: nothing here is loaded into a session.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Security

Grade A, and why

pluck scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/claude-code/.mcp.json · 9 lines

What it actually says

{
  "pluck": {
    "command": "pluckd",
    "args": [
      "--repo",
      "${REPO_ROOT}"
    ]
  }
}

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

2d ago First seen · 9 lines scan A 7a40a12c5740

Subscribe to this mod's changes

pluck is an MCP server published in the GitHub repository hunhee98/pluck (40 stars, last pushed 3mo ago), licensed MIT. Its token cost is not measured: an MCP server costs its tool schemas, not its config file. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Memory and context Research ai-agents bm25 claude-code cli code-intelligence code-search

codenib

A multi-view data system for serving repository context to coding agents. Runs locally from the codenib Python package.

sysevol-ai/CodeNib · not measured

sverklo

MCP server "sverklo" as configured in sverklo/sverklo. Launched with /opt/homebrew/bin/sverklo .. Needs 1 environment variable to run.

sverklo/sverklo · not measured

codestory

MCP server "codestory" as configured in TheGreenCedar/CodeStory. Runs ./scripts/codestory-mcp.cjs with node.

TheGreenCedar/CodeStory · not measured

code-context

Local code search for AI coding agents: a CLI and MCP server with hybrid keyword + semantic search and SQL relevance-ranked aggregation over an index that lives in plain files. No accounts, no keys, no server. Runs locally from the @infino-ai/code-context npm package.

infino-ai/code-context · not measured

leantoken

MCP server "leantoken" as configured in morluto/leantoken. Launched with leantoken.

morluto/leantoken · not measured

coldstart

Codebase memory for AI agents: an AST index plus agent-written notes that self-stale. Runs locally from the @cstart/coldstart npm package.

AkashGoenka/coldstart · not measured