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.
git clone --depth 1 https://github.com/ksylvan/fabric-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/mcp/ksylvan/fabric-mcp/fabricmcp)<a href="https://agentmods.dev/mcp/ksylvan/fabric-mcp/fabricmcp"><img src="https://agentmods.dev/badge/mcp/ksylvan/fabric-mcp/fabricmcp/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/mcp/ksylvan/fabric-mcp/fabricmcp"><img src="https://agentmods.dev/badge/mcp/ksylvan/fabric-mcp/fabricmcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket warn
Grade A, and why
FabricMCP 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
{
"FabricMCP": {
"type": "stdio",
"command": "uv",
"args": [
"run",
"fabric-mcp",
"--transport",
"stdio"
],
"cwd": "${workspaceFolder}"
}
}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 · 13 lines scan A 9ab1a79b04df
FabricMCP is an MCP server published in the GitHub repository ksylvan/fabric-mcp (90 stars, last pushed 4d 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 2026-10-12.
Other mcp servers, from other repositories
metamcp
Route long-tail MCP servers through three lazy tools and reviewed declarative Methods. Runs locally from the @mentu/metamcp npm package.
iso27001-mcp
ISO 27001 compliance workspace for Claude. Risks, policies, SoA, evidence, and audit workflows. Runs locally from the iso27001-mcp npm package. Needs 4 environment variables to run.
wet-mcp
Open-source MCP Server for web search, extract, crawl, academic research, and library docs with embedded SearXNG. Runs locally from the wet-mcp Python package. Needs 2 environment variables to run.
mnemo-mcp
Open-source MCP Server for persistent AI memory with embedded sync. Runs locally from the mnemo-mcp Python package. Needs 1 environment variable to run.
rowlite
MCP server "rowlite" as configured in pipik-roman/rowlite. Launched with https://github.com/pipik-roman/rowlite/releases/download/v0.3.0/rowlite_0.3.0_li.
learning-orchestrator-mcp
MCP server "learning-orchestrator-mcp" as configured in SEOSiri-Official/learning-orchestrator-mcp. Runs locally from the learning-orchestrator-mcp Python package.