seerr-mcp-server AGENTS.md

seerr-mcp-server AGENTS.md is an instructions file for Codex, OpenCode from cyanheads/seerr-mcp-server. It costs 6,638 tokens per session, scanned A, a copy of obsidian-mcp-server AGENTS.md, Apache-2.0.

Developer instructions for a server that lets an assistant search and request films and TV shows through a self-hosted Jellyseerr or Overseerr service.

In plain words
What is it for?
Use them when developing or reviewing this server's six tools and one request resource, including media search, availability checks, request creation, and request status.
Why use it?
They explain the server's boundaries, supported operations, framework versions, and rules that changes must preserve.

Instructions file for CodexOpenCode

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 instructions/cyanheads/seerr-mcp-server/agents-md
Clone the repo
git clone --depth 1 https://github.com/cyanheads/seerr-mcp-server

Made for: Codex, 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 seerr-mcp-server AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/cyanheads/seerr-mcp-server/agents-md.svg)](https://agentmods.dev/instructions/cyanheads/seerr-mcp-server/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/cyanheads/seerr-mcp-server/agents-md"><img src="https://agentmods.dev/badge/instructions/cyanheads/seerr-mcp-server/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 6,638 This file is loaded in full into every session.
When invoked 6,638 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin 72% copy Near-identical to another mod in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.06638 $0.06638
Opus 5 $0.03319 $0.03319
Sonnet 5 $0.01328 $0.01328
Haiku 4.5 $0.00664 $0.00664

Measured 4d ago against content hash 90db5e909fef, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

seerr-mcp-server 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.

Origin

This is a copy

72% identical to obsidian-mcp-server AGENTS.md — 342 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

AGENTS.md · 413 lines

How it starts

The opening of the file, as written. The whole thing — 413 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Developer Protocol

Server: seerr-mcp-server Version: 0.1.3 Framework: @cyanheads/mcp-ts-core ^0.12.3 Engines: Bun ≥1.3.0, Node ≥24.0.0 MCP SDK: @modelcontextprotocol/server ^2.0.0 Zod: ^4.4.3

Read the framework docs first: node_modules/@cyanheads/mcp-ts-core/CLAUDE.md contains the full API reference — builders, Context, error codes, exports, patterns. This file covers server-specific conventions only.


What This Server Does

A workflow MCP server over a self-hosted Jellyseerr/Overseerr instance: search → confirm the TMDB-backed title → check availability/request state → create a guarded request that Radarr/Sonarr act on. Jellyseerr owns permissions, quotas, routing, and status; this server never touches Radarr/Sonarr directly. Read + guarded-request only — admin-scope endpoints (approve/decline, retry, edit/delete, media/file deletion, user/settings/sync) are excluded by design.

Surface: six tools (seerr_search_media, seerr_get_media, seerr_list_requests, seerr_request_media, seerr_request_status, seerr_service_options) + one resource (seerr://request/{requestId}). No prompts.

Two invariants that must never regress:

  1. Guarded write. seerr_request_media is the only mutation. It defaults to mode: preview (resolve + validate, no POST); the real write fires only on mode: request and only once the handler is re-entered with a schema-valid acceptance on ctx.inputs, with destructiveHint: true surfacing the risk in client-side approval flows. There is no branch that proceeds without an acceptance — a client that never answers leaves the write un-run. Capability validation (4K/seasons/partial) runs locally against cached settings before any POST. MCP_SESSION_MODE must resolve to stateful: the round trip needs a live session for 2025-era clients, and stateless refuses it.
  2. PII/infra redaction. Every raw Jellyseerr payload is projected through src/services/seerr/normalizers.ts — the single choke point — before output. It allow-lists fields: User{ id, displayName }, and drops operator email, Plex/Jellyfin tokens, serviceUrl, vapidPublic, and filesystem paths (gated behind includePaths). The base URL and API key live only in config and never appear in output. Redaction lives in normalizers, not format(), so both structuredContent and content[] are clean. ctx.log is a third output surface — it is dual-sink as of mcp-ts-core 0.12.0, mirroring every call to the client as notifications/message — so log only classified reasons and the caller's own inputs, never a raw upstream or network message.

Read the full file on GitHub · 413 lines

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. 4d ago First seen · 413 lines · 6,638 tokens per session scan A 90db5e909fef

Subscribe to this mod's changes

seerr-mcp-server AGENTS.md is an instructions file published in the GitHub repository cyanheads/seerr-mcp-server (1 stars, last pushed 10d ago), licensed Apache-2.0. It adds 6,638 tokens to every session, about $0.0332 per session on Opus 5. A static security scan graded it A with 0 findings. It is 72% identical to obsidian-mcp-server AGENTS.md, differing in 342 lines, and is treated as a copy.