Borrowing it
Nothing to install: this file belongs to metanmai/libredesk-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/metanmai/libredesk-mcp/main/AGENTS.mdgit clone --depth 1 https://github.com/metanmai/libredesk-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/metanmai/libredesk-mcp/agents-md)<a href="https://agentmods.dev/instructions/metanmai/libredesk-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/metanmai/libredesk-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 5.1 | $0.02306 | $0.02306 |
| Opus 5 | $0.01153 | $0.01153 |
| Sonnet 5 | $0.00461 | $0.00461 |
| Haiku 4.5 | $0.00231 | $0.00231 |
Grade A, and why
libredesk-mcp AGENTS.md scanned grade A with 1 finding 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 7d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
`src/openapi.json` is a manual copy from `https://docs.libredesk.io/api-reference/openapi.json`. It is not auto-generated during build. Updating it requires a manual curl+copy. The build script only copies it into `dist/ How it starts
The opening of the file, as written. The whole thing — 187 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Project overview
libredesk-mcp is a single-file MCP (Model Context Protocol) server that exposes the Libredesk REST API as MCP tools. It dynamically generates all tools at startup from a bundled OpenAPI 3.0 spec. ~54 endpoints become MCP tools.
- Language: TypeScript (ESM —
"type": "module"in package.json) - Runtime: Node.js ≥ 18
- MCP SDK:
@modelcontextprotocol/sdkv1 - Transport: stdio (JSON-RPC over stdin/stdout)
- Single source file: all logic lives in
src/index.ts(~390 lines). Key functions are exported for testability;main()is guarded to only run when executed directly (not when imported).
Essential commands
npm install # install dependencies
npm run build # tsc → dist/ + copy openapi.json into dist/
npm start # run compiled output (node dist/index.js)
npm test # run vitest unit tests
npm run test:watch # vitest in watch mode
npm run fetch-spec # update bundled OpenAPI spec from upstream
There is a test suite (vitest, 38 tests) and CI (GitHub Actions with build, test, and Docker integration). There is no linter.
Architecture
src/
├── index.ts # Everything: spec loader, tool builder, MCP server, HTTP client
└── openapi.json # Bundled copy of Libredesk's OpenAPI 3.0 spec (~4800 lines)
Startup flow
main()loadsopenapi.jsonfromdist/(or falls back tosrc/during dev viatsx)buildTools()walks every path+method in the spec, flattens parameters and request bodies into MCP tool schemas- Tools are registered via
ListToolsRequestSchema/CallToolRequestSchemahandlers on the MCPServer - Server connects via
StdioServerTransportand logs readiness to stderr
Tool generation (buildTools)
For each operation in the OpenAPI spec:
- Name: derived from
operationIdby stripping ahandleprefix, splitting camelCase into snake_case (with consecutive-uppercase acronym handling), then lowercasing. Examples:handleGetConversation→get_conversation,handleGetAIPrompts→get_ai_prompts,handleGenerateAPIKey→generate_api_key. Constrained to ≤ 60 chars. - Description: concatenates summary, description, HTTP method/path, and tags
- inputSchema: type
"object"withadditionalProperties: true. Properties are built from:- Path parameters (always required)
- Query parameters (required if marked so in spec)
- Request body properties (dereferenced from
$refs). JSON body fields get the spec description prefixed with(body). If a body field name collides with a path/query param, it gets abody_prefix.
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.
- 7d ago First seen · 187 lines · 2,306 tokens per session scan A efefdeb2bbfc
libredesk-mcp AGENTS.md is an instructions file published in the GitHub repository metanmai/libredesk-mcp (3 stars, last pushed 3mo ago), licensed MIT. It adds 2,306 tokens to every session, about $0.0115 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.