A local MCP server for searching a codebase by meaning, using configurable text-embedding providers, vector databases, and data sources. MCP is a standard way for tools to provide capabilities to an AI agent.

It helps an agent perform semantic code searches from the current project through the CodeWeaver Python package.

It helps find related code when the exact name or wording is unknown, but it requires four environment variables to run.

codeweaver — MCP server by knitli

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/knitli/toolshed/codeweaver-codeweaver

Clone the repo

git clone --depth 1 https://github.com/knitli/toolshed

Made for: Claude Code, Codex, Cursor.

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

codeweaver 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/codeweaver/.mcp.json · 21 lines

What it actually says

{
  "codeweaver": {
    "command": "uvx",
    "args": [
      "--from",
      "code-weaver",
      "cw",
      "server",
      "--transport",
      "stdio",
      "--project",
      "${workspaceFolder}"
    ],
    "env": {
      "XDG_DATA_HOME": "${CLAUDE_PLUGIN_DATA}/data",
      "XDG_CACHE_HOME": "${CLAUDE_PLUGIN_DATA}/cache",
      "XDG_STATE_HOME": "${CLAUDE_PLUGIN_DATA}/state",
      "XDG_CONFIG_HOME": "${CLAUDE_PLUGIN_DATA}/config"
    }
  }
}

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 · 21 lines scan A 55248e3f22a3

Subscribe to this mod's changes

codeweaver is an MCP server published in the GitHub repository knitli/toolshed (1 stars, last pushed 4mo 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 2026-08-31.

Data and AI RAG and vectors claude-code-plugin claude-skills codex-plugin codex-skills gemini-plugin gemini-skills

codeweaver

Getting it into your agent

Grade A, and why

Nothing flagged

What it actually says

What this file has done since we first saw it

Other mcp servers, from other repositories

dev-flow

edgespark-docs

sitescrape

docs-langchain

reference-langchain

playwright-test