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/arr-mcps/seerr-mcp/agents-mdgit clone --depth 1 https://github.com/arr-mcps/seerr-mcpWhat 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 | $0.01714 | $0.01714 |
| Opus 5 | $0.00857 | $0.00857 |
| Sonnet 5 | $0.00343 | $0.00343 |
| Haiku 4.5 | $0.00171 | $0.00171 |
Grade A, and why
seerr-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 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.
How it starts
The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — seerr-mcp
MCP server exposing Seerr's v1 REST API (OpenAPI 3.0.2) as tools so an LLM can
read and manage a Seerr instance: search and discovery, media requests and
approvals, users, issues, watchlists and blocklists, Plex/Jellyfin/Emby and
Sonarr/Radarr settings, notification agents, jobs, and more. Full surface —
reads and writes. Uses FastMCP, uv for deps.
Exposed as 15 resource-scoped portmanteau tools, not one tool per endpoint — see "Tool registry and the spec" below. A prior version registered all 208 endpoints individually; that blew the MCP context budget (~208 tools × ~250 tokens ≈ 52k tokens just for this one server) and has been retired. Seerr's own domain shape (settings-heavy — seerr_settings_general + seerr_settings_notifications alone cover 82/208 endpoints) means its _GROUPS taxonomy is its own, not shared with radarr/sonarr/bookshelf.
Testing
- Offline suite:
make test(oruv run pytest) - Live integration (needs
SEERR_URL/SEERR_API_KEY):make test-integration- GET endpoints run against the live instance.
- POST/PUT/DELETE only run when
SEERR_WRITE_TESTS=1, as a safe create→delete cycle against a scratch blocklist entry, then cleanup. Never point write tests at a production instance.
Tool registry and the spec
_TOOL_REGISTRYinseerr_mcp.pyis generated from the vendored spec attests/data/seerr_openapi.yml(pinned to seerr-team/seerr develop HEAD39ff48c650d30ced0516574c55914d0bd26c9983). It lists every JSON-producing endpoint under/api/v1.- Excluded on purpose: the deprecated
/blacklist/*aliases (sunset 2026-06-01) — the/blocklist/*routers cover the same handlers._reqJSON-decodes every response. - To add a tool or refresh coverage, regenerate the registry from a newer
seerr-api.yml:
then splice the printeduv run python scripts/generate_registry.py_TOOL_REGISTRYintoseerr_mcp.py, update the SHA intests/data/README.md/seerr_mcp.py/AGENTS.md, and re-run the tests. Do not hand-edit the registry. - Endpoint function naming (internal, no longer an MCP tool name):
seerr_<verb>_<resource>derived from method + path (e.g.seerr_list_request,seerr_create_request,seerr_delete_request,seerr_set_request_status). Flagship/action endpoint overrides and collision fixes live inNAME_OVERRIDESinscripts/generate_registry.py.
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 · 84 lines · 1,714 tokens per session scan A 974bedc7d1bd
seerr-mcp AGENTS.md is an instructions file published in the GitHub repository arr-mcps/seerr-mcp (0 stars, last pushed 8d ago), licensed MIT. It adds 1,714 tokens to every session, about $0.0086 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
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).
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.
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.
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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.