talonic-mcp AGENTS.md

talonic-mcp AGENTS.md is an instructions file for Codex, OpenCode from talonicdev/talonic-mcp. It costs 3,010 tokens per session, scanned A, original, MIT.

Repository instructions for Talonic MCP, a Node package that exposes a document-extraction service to AI tools through the Model Context Protocol. It explains the local command-line setup, hosted server, repository layout, publishing process, and two separate documentation locations.

In plain words
What is it for?
Use it when working on the Talonic MCP server, its local or hosted connection, document-extraction tools, documentation, tests, or publishing workflow.
Why use it?
It prevents changes from going into the wrong documentation source, a mistake that can make updates silently diverge or fail to appear.

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/talonicdev/talonic-mcp/agents-md
Clone the repo
git clone --depth 1 https://github.com/talonicdev/talonic-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.

agentmods badge for talonic-mcp AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/talonicdev/talonic-mcp/agents-md.svg)](https://agentmods.dev/instructions/talonicdev/talonic-mcp/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/talonicdev/talonic-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/talonicdev/talonic-mcp/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 3,010 This file is loaded in full into every session.
When invoked 3,010 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.03010 $0.03010
Opus 5 $0.01505 $0.01505
Sonnet 5 $0.00602 $0.00602
Haiku 4.5 $0.00301 $0.00301

Measured 4d ago against content hash a12caf9fce23, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

talonic-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 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.

AGENTS.md · 157 lines

How it starts

The opening of the file, as written. The whole thing — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — Orientation for AI agents working in talonic-mcp

This is the canonical agent-facing guide for this repository. It is read by Claude Code, Cursor, Codex, and other agent tools that look for AGENTS.md. CLAUDE.md is a short Claude Code entry point that points here.

This repo is the Talonic MCP server — a Node package (@talonic/mcp) that exposes Talonic's document-extraction API as Model Context Protocol tools. It runs two ways from one codebase:

  • stdio — for local installs (Claude Desktop, Cursor, Cline, Continue, Cowork) launched via npx @talonic/mcp.
  • Streamable HTTP — the hosted server at mcp.talonic.com, used by Claude.ai connectors.

⚠️ #1 footgun: there are TWO parallel docs surfaces

Before changing any documentation content, internalise this — it has caused weeks of silent drift:

Edit this… …to change this page
src/content/sections/*.ts@talonic/mcp/content talonic.com/docs/mcp/* (the MCP docs)
docs/sections.json@talonic/docs (synced via the platform repo) the mcp content domain of @talonic/docs, which no page currently rendersNOT /docs/mcp/, and not /docs/{sdk,api,platform}/* either

If you edit docs/sections.json expecting the MCP docs page to change, nothing on /docs/mcp will move. Full architecture, the four-file checklist for adding a tool, the failure-mode table, and the CI-token map live in docs/architecture/docs-pipeline.md — read it before any non-trivial doc change.

README.md, CHANGELOG.md, STATUS.md, and this file are repo-local and feed neither website surface; they're for developers and agents reading the repo directly.


The sixteen public tools (and what an agent should reach for)

Source: one file per tool in src/tools/. Each exports handle<Name>() (pure, unit-tested) and register<Name>() (wires it into the MCP server).

Internal exception — src/tools/growth.ts registers four Talonic-internal, superadmin-only growth-analytics tools (talonic_growth_*) against the platform's /v1/growth/* surface. They are registered CONDITIONALLY: both entrypoints call probeGrowthAccess() and include them only when the session's credential passes the platform's superadmin gate (hosted: per-token 5-min cache in http-server.ts; stdio: once at boot). The platform re-checks the principal on every call, so the probe is listing UX, never the security boundary. Deliberately absent from BOTH public docs surfaces — do not add them to src/content/ or docs/sections.json.

Read the full file on GitHub · 157 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 · 157 lines · 3,010 tokens per session scan A a12caf9fce23

Subscribe to this mod's changes

talonic-mcp AGENTS.md is an instructions file published in the GitHub repository talonicdev/talonic-mcp (5 stars, last pushed today), licensed MIT. It adds 3,010 tokens to every session, about $0.0151 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.