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/contentful/contentful-mcp-server/agents-mdgit clone --depth 1 https://github.com/contentful/contentful-mcp-serverWrote 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/contentful/contentful-mcp-server/agents-md)<a href="https://agentmods.dev/instructions/contentful/contentful-mcp-server/agents-md"><img src="https://agentmods.dev/badge/instructions/contentful/contentful-mcp-server/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 | $0.00868 | $0.00868 |
| Opus 5 | $0.00434 | $0.00434 |
| Sonnet 5 | $0.00174 | $0.00174 |
| Haiku 4.5 | $0.00087 | $0.00087 |
Grade A, and why
contentful-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.
How it starts
The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Guide
Read this file first. It tells you where to find context in this repo.
Quick Reference
| What you need | Where to look |
|---|---|
| How this repo is structured | ARCHITECTURE.md |
| How to build/test/run | CONTRIBUTING.md |
| Why decisions were made | docs/ADRs/ |
| What this repo does | README.md |
| PR review rules | .bito/guidelines/ |
| Active specs/work | docs/specs/ |
| MCP tool implementations | packages/mcp-tools/src/tools/ |
| Server entry point | packages/mcp-server/src/index.ts |
Sharp Edges & Invariants
- Always call
get_initial_contextfirst — the server's agent instructions require this as the first tool call in every session. It initializes connection context and returns space metadata. - Entry mutation limit: 5 per conversation — the system prompt enforces a max of 5 entry create/edit/mutate operations at a time.
- ESM-only — both packages output ESM. All internal imports must use
.jsextensions (even in.tssource files). - Migration tools are disabled by default —
export_space,import_space, andspace_to_space_param_collectionare registered but disabled. Onlyspace_to_space_migration_handlercan enable them. contentful-exportandcontentful-importare lazy-loaded — they are dynamically imported at runtime to avoid bundling their large dependency trees when not needed.- Zod schemas define tool input contracts — every tool uses Zod for input validation. The
.shapeproperty of the schema is passed to MCP SDK for client-side validation hints. X-Contentful-User-Agent-Toolheader — all CMA calls include this header with the MCP version. Do not remove or change the header name; it's used for observability.- Never hardcode space/environment IDs in tool implementations — always read from
ContentfulConfigor tool input params. contentful-managementuses namespace imports — since CMA v12, useimport * as ctfl from 'contentful-management'(not default import).
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 · 61 lines · 868 tokens per session scan A b6c53e1bf230
contentful-mcp-server AGENTS.md is an instructions file published in the GitHub repository contentful/contentful-mcp-server (60 stars, last pushed 2d ago), licensed MIT. It adds 868 tokens to every session, about $0.0043 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 2026-08-30.
Other instructions, from other repositories
contentful.net AGENTS.md
Instructions for contentful/contentful.net, covering agent guide, quick reference, sharp edges & invariants, key conventions and integration points.
payload CLAUDE.md
Claude Code instructions for payloadcms/payload, covering claude.md, project structure, key directories, architecture notes and quick start.
payload AGENTS.md
AGENTS.md instructions for payloadcms/payload, a project described as: Payload is the open-source, fullstack Next.js framework, giving you instant backend superpowers. Get a full TypeScript backend and admin panel instantly. Use Payload as a headless CMS or for building powerful applications.
intlayer CLAUDE.md
Claude Code instructions for aymericzip/intlayer, covering repo layout, commands (run from root), content declaration flow, git and commit conventions.
contentful.js AGENTS.md
AGENTS.md instructions for contentful/contentful.js, covering agent guide, quick reference, sharp edges & invariants, key conventions and integration points.
contentful.php AGENTS.md
Instructions for contentful/contentful.php, covering agent guide, quick reference, sharp edges & invariants, key conventions and integration points.