agentmods.dev

filesystem

filesystem is an MCP server for Claude Code, Codex, Cursor, Gemini CLI, OpenCode from configflux/weld. Its token cost is not measured, scanned A, original, Apache-2.0.

A local file-access service that provides an agent with context from repository files. MCP is a standard way for AI tools to connect to external services.

In plain words
What is it for?
Use it when an agent needs to inspect or use files from a local software repository.
Why use it?
It lets an agent work with files stored in a local project instead of relying only on text copied into the conversation.

MCP server for Claude CodeCodexCursorGemini CLIOpenCode

Written for no agent in particular: it speaks MCP, so any client can run it. Also seen: listed in a Claude config.

One of 2 entries in .mcp.json — they are configured in one file and arrive together.

not rated 6 3d ago A scan tokens not measured original Apache-2.0
View the source file configflux/weld
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/configflux/weld/agent-graph-demo-filesystem
Clone the repo
git clone --depth 1 https://github.com/configflux/weld

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

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for filesystem

README.md
[![agentmods](https://agentmods.dev/badge/mcp/configflux/weld/agent-graph-demo-filesystem.svg)](https://agentmods.dev/mcp/configflux/weld/agent-graph-demo-filesystem)
Your own site
<a href="https://agentmods.dev/mcp/configflux/weld/agent-graph-demo-filesystem"><img src="https://agentmods.dev/badge/mcp/configflux/weld/agent-graph-demo-filesystem.svg" alt="Measured on agentmods" height="20"></a>
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

filesystem 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 6d 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.

examples/agent-graph-demo/.mcp.json · 5 lines

What it actually says

{
  "filesystem": {
    "description": "Local repository file context."
  }
}
Same file

What else .mcp.json configures

This page is one entry in a file that holds 2. Installing the file brings all of them; each is measured and scanned on its own page.

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.

  1. 6d ago First seen · 5 lines scan A 1041285c009a

Subscribe to this mod's changes

filesystem is an MCP server published in the GitHub repository configflux/weld (6 stars, last pushed 3d ago), licensed Apache-2.0. 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.

ai-agentsastclaude-codecode-intelligencecodebase-analysisdeveloper-tools
Related

Other mcp servers, from other repositories

astra-code-context

MCP server "astra-code-context" as configured in nimelkot/astra. Runs locally from the astra-code-context Python package.

nimelkot/astra · not measured

sem

Entity-level code intelligence: semantic diff, impact analysis, blame, and context for AI agents. Runs locally from the @ataraxy-labs/sem npm package.

Ataraxy-Labs/sem · not measured

gograph

MCP server "gograph" as configured in ozgurcd/gograph. Launched with https://github.com/ozgurcd/gograph/releases/download/v1.6.8/gograph_1.6.8_darwin.

ozgurcd/gograph · not measured

agent-lsp

Stateful LSP runtime for AI agents — 50+ tools across 30+ languages via MCP. Runs locally from the @blackwell-systems/agent-lsp npm package.

blackwell-systems/agent-lsp · not measured

code-index

Rust code index MCP server, native 1C:Enterprise (BSL) support. 32 tools, AST for 14 languages. Runs locally from the @regsorm/code-index-mcp npm package.

Regsorm/code-index-mcp · not measured

m1nd

MCP server "m1nd" as configured in maxkle1nz/m1nd. Launched with m1nd-mcp --stdio --no-gui. Needs 1 environment variable to run.

maxkle1nz/m1nd · not measured