What is discourse-mcp AGENTS.md?

Project instructions for developing the Discourse MCP server, which gives AI agents access to Discourse forum capabilities.

Use them when building, checking, testing, cleaning, or extending Discourse MCP tools and workflows.

They show where the server’s tools, resources, HTTP client, tests, and command-line entry point live, reducing guesswork when changing the code.

How discourse/discourse-mcp configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to discourse/discourse-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.

Copy the file

curl -O https://raw.githubusercontent.com/discourse/discourse-mcp/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/discourse/discourse-mcp

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/discourse/discourse-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/discourse/discourse-mcp/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/discourse/discourse-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/discourse/discourse-mcp/agents-md/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/discourse/discourse-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/discourse/discourse-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,809 This file is loaded in full into every session.

When invoked 1,809 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found 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.

Model	Per session	Once invoked
Fable 5.1	$0.01809	$0.01809
Opus 5.5	$0.00724	$0.00724
Sonnet 5.5	$0.00362	$0.00362
Haiku 4.5	$0.00181	$0.00181

Measured 3d ago against content hash ebf7f1727203, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

discourse-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 3d 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.

AGENTS.md · 156 lines

How it starts

The opening of the file, as written. The whole thing — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — Discourse MCP

MCP server exposing Discourse forum capabilities as tools/resources for AI agents. Entry: src/index.ts → dist/index.js (binary: discourse-mcp). Node >= 24.

SDLC Commands

pnpm build       # Compile TypeScript to dist/
pnpm typecheck   # Type-check only (no emit)
pnpm lint        # Run ESLint on src/
pnpm test        # Run tests (requires build first)
pnpm clean       # Remove dist/

Source Map

Area	Files
Entry/CLI	`src/index.ts`
HTTP client	`src/http/client.ts`
Bounded directories	`src/site/directories.ts`
Tool registry	`src/tools/registry.ts`
Tool definitions/catalog	`src/tools/definition.ts`, `src/tools/builtin/catalog.ts`
Built-in toolsets	`src/tools/toolsets.ts`
Resource registry	`src/resources/registry.ts`
Built-in tools	`src/tools/builtin/*`
Tag-group lifecycle	`src/tools/builtin/tag_groups/*`
Workflow tools/adapters	`src/tools/builtin/workflows/*`
Remote tools	`src/tools/remote/tool_exec_api.ts`
Utilities	`src/util/*.ts` (logger, redact, json_response)

Key Patterns

Tool Implementation

Tools live in src/tools/builtin/ as typed defineTool({...}) definitions
src/tools/builtin/catalog.ts is the ordered built-in collection; src/tools/registry.ts registers it through the shared registrar
Every definition declares two independent registration dimensions:
- availability is one mutually exclusive configuration gate: always, writes_enabled, or site_selection
- toolsets is a non-empty list of operator-facing domains; selected domains form a union while preserving catalog order
OPT_IN_TOOLSETS domains are hidden when selection is omitted; --toolsets all expands to every real domain. Definitions must not mix opt-in and default memberships.
Availability is not domain metadata, and toolsets do not replace write, authentication, or admin checks
All tools return strict JSON (no Markdown) with isError: true on failure
Tools with outputSchema must validate normalized upstream data in the handler and use structuredJsonResponse() so structuredContent equals the JSON text fallback. Keep malformed/error results unstructured and isError: true.
Write tools use writes_enabled and retain a call-time access check; they require --allow_writes and matching auth_pairs

Read the full file on GitHub · 156 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.

3d ago Changed ebf7f1727203
2mo ago First seen · 156 lines · 1,809 tokens per session scan A df7d394bc887

Subscribe to this mod's changes

discourse-mcp AGENTS.md is an instructions file published in the GitHub repository discourse/discourse-mcp (79 stars, last pushed 3d ago), licensed MIT. It adds 1,809 tokens to every session, about $0.0072 per session on Opus 5.5. 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 2026-08-30.

discourse-mcp AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
discourse-mcp AGENTS.mddiscourse/discourse-mcp	Instructions file	79	3d ago	MIT	A	1,809	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	2,022	GitHub Copilot

discourse-mcp: Instructions file for Codex