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/talonicdev/talonic-mcp/agents-mdgit clone --depth 1 https://github.com/talonicdev/talonic-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/talonicdev/talonic-mcp/agents-md)<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>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 | $0.03010 | $0.03010 |
| Opus 5 | $0.01505 | $0.01505 |
| Sonnet 5 | $0.00602 | $0.00602 |
| Haiku 4.5 | $0.00301 | $0.00301 |
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.
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.mdis 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 renders — NOT /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.
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.
- 4d ago First seen · 157 lines · 3,010 tokens per session scan A a12caf9fce23
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.
Other instructions, from other repositories
langgraph AGENTS.md
AGENTS.md instructions for langchain-ai/langgraph, covering agents instructions, corridor security analysis, libraries and dependency map.
Browser4 CLAUDE.md
Claude Code instructions for platonai/Browser4, covering browser4 — project context for claude, architecture, key dispatch chain (cli → browser), batch commands and e2e test structure.
fast-browser CLAUDE.md
Claude Code instructions for m4ttstack/fast-browser, covering fast browser plugin, where a change belongs, fork branch: use fast-browser-runtime, releasing a new runtime and re-pinning this repo: use the script.
sendblue-browser-use AGENTS.md
Instructions for sendblue-api/sendblue-browser-use, covering agents.md — sendblue-browser-use, what this repo is, setup, common commands and health (no auth).
sniff AGENTS.md
AGENTS.md instructions for Aboudjem/sniff, covering agents.md: sniff, what this repo is, how an agent should use sniff, handling the playwright setup gate and finding output schema.
browser_oxide AGENTS.md
AGENTS.md instructions for yfedoseev/browser_oxide, covering browseroxide — conventions for ai coding assistants, build & test, architecture, key conventions and where to read more.