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.
npx agentmods add instructions/sandraschi/filesystem-mcp/agents-mdgit clone --depth 1 https://github.com/sandraschi/filesystem-mcpWrote 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.
[](https://agentmods.dev/instructions/sandraschi/filesystem-mcp/agents-md)<a href="https://agentmods.dev/instructions/sandraschi/filesystem-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/sandraschi/filesystem-mcp/agents-md.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00322 | $0.00322 |
| Opus 5 | $0.00161 | $0.00161 |
| Sonnet 5 | $0.00064 | $0.00064 |
| Haiku 4.5 | $0.00032 | $0.00032 |
Grade A, and why
filesystem-mcp AGENTS.md 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 4d 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.
What it actually says
filesystem-mcp — Agent Guide
Overview
FastMCP 3.2+ server for file system, Docker, system monitoring, and host context operations.
Tools
23 tools across 10 modules. Portmanteau tools use an operation enum parameter.
| Tool | Category | Mutates |
|---|---|---|
file_ops |
File read/write/edit/delete/move/copy | Yes |
dir_ops |
Directory list/create/remove | Some |
search_ops |
Grep, search, compare, find duplicates | No |
container_ops |
Docker container lifecycle | Yes |
infra_ops |
Docker images, networks, volumes | Yes |
compose_up/down/ps/logs/config/restart |
Docker Compose | Some |
monitor_get_* (8 tools) |
System metrics | No |
host_ops |
Host info and environment | No |
agentic_file_workflow |
LLM sampling-based file ops | Yes |
get_lock_status |
Concurrency lock diagnostics | No |
Ports
- Backend: 10742
- Frontend: 10743
Key Standards
- Concurrency-safe writes: per-path
asyncio.Lock+ atomicos.replace() - Structured responses:
_success_response,_error_response,_clarification_response - Dual transport: stdio (Claude Desktop) + HTTP (webapp)
Install docs: follow mcp-central-docs/standards/AGENT_INSTALL_REFERENCE.md
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.
- 4d ago First seen · 32 lines · 322 tokens per session scan A b384877775d7
filesystem-mcp AGENTS.md is an instructions file published in the GitHub repository sandraschi/filesystem-mcp (6 stars, last pushed 4d ago), licensed MIT. It adds 322 tokens to every session, about $0.0016 per session on Opus 5. 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.
Other instructions, from other repositories
freecad-mcp AGENTS.md
AGENTS.md instructions for sandraschi/freecad-mcp, covering freecad-mcp — agent guide, core capabilities for fleet agents, standards & patterns and key files & structure.
freecad-mcp copilot-instructions.md
Copilot instructions for sandraschi/freecad-mcp: You have access to 46+ FreeCAD CAD/CAM/CAE tools via MCP.
freecad-mcp CLAUDE.md
Claude Code instructions for sandraschi/freecad-mcp, covering freecad-mcp — claude code guide, standards and key files.
qcad-mcp AGENTS.md
AGENTS.md instructions for sandraschi/qcad-mcp, covering qcad-mcp — agent guide, ports, key commands, standards and key files.
qcad-mcp CLAUDE.md
Claude Code instructions for sandraschi/qcad-mcp, covering qcad-mcp — claude code guide, standards and key files.
blender-mcp AGENTS.md
AGENTS.md instructions for sandraschi/blender-mcp, covering blender-mcp agent context and quick ref.