Working with Agents

How to connect AI agents, LLMs, and automation tools to your documentation.

Whether you're feeding documentation to Claude, ChatGPT, a custom LLM pipeline, or a CI/CD script, AgentDocs provides multiple integration points:

MCP Server — the fastest integrationRecommended

If your agent runs in a client that can launch a local MCP server (Claude Code, Claude Desktop, Cursor, Windsurf), you can skip raw REST: the official MCP server exposes AgentDocs as 14 native tools (keyword and semantic search, read, create, update, append, markdown-folder import, share and more), addressable by slug or UUID. Works with account tokens and space-scoped tokens alike. On Claude.ai web, upload the Skill instead (a hosted remote connector is on the roadmap).

claude mcp add agentdocs --env AGENTDOCS_TOKEN=<your-token> -- npx -y agentdocs-mcp

Any other MCP client can launch the same server with this standard config:

{
  "mcpServers": {
    "agentdocs": {
      "command": "npx",
      "args": ["-y", "agentdocs-mcp"],
      "env": { "AGENTDOCS_TOKEN": "<your-token>" }
    }
  }
}

github.com/hoornet/agentdocs-mcp · npmjs.com/package/agentdocs-mcp

The Agent-Friendly Raw Endpoint

The raw endpoint is the recommended way to give AI agents access to your documentation. It returns pure Markdown text with YAML frontmatter — no HTML, no JSON wrapping, no authentication required.

Response Format

The response is plain text (Content-Type: text/markdown; charset=utf-8) with the following structure:

---
title: Deployment Guide
shared_via: AgentDocs
last_updated: 2025-01-15T10:30:00.000Z
---

# Deployment Guide

This guide covers how to deploy the application to production.

## Prerequisites

- Docker 20.10+
- Kubernetes 1.25+
- Access to the container registry

## Steps

1. Build the container image:
   ```bash
   docker build -t myapp:latest .
   ```

2. Push to the registry:
   ```bash
   docker push registry.example.com/myapp:latest
   ```

3. Apply the Kubernetes manifests:
   ```bash
   kubectl apply -f k8s/
   ```

YAML Frontmatter Fields

Getting the Agent Link

The easiest way to get an agent-friendly URL:

Example: Fetching from the Command Line

# Fetch the raw markdown for a shared page
curl https://agentdocs.eu/api/shared/abc123def456.../raw

# Response:
# ---
# title: Deployment Guide
# shared_via: AgentDocs
# last_updated: 2025-01-15T10:30:00.000Z
# ---
#
# # Deployment Guide
# ...

# You can also pipe it directly to other tools:
curl -s https://agentdocs.eu/api/shared/abc123.../raw | head -20

Practical Examples

Feeding Docs to Claude / ChatGPT

You can include an AgentDocs raw URL in your AI assistant's system prompt or tool definition to give it access to always-up-to-date documentation:

# In a system prompt or instruction set:

You have access to our deployment documentation.
Fetch the latest version from:
https://agentdocs.eu/api/shared/abc123def456/raw

Use this documentation to answer questions about
deployment procedures, troubleshooting, and configuration.

Using in MCP Tool Definitions

If your agent framework supports tools/functions, you can define a tool that fetches doc pages:

{
  "name": "get_deployment_docs",
  "description": "Fetch the latest deployment documentation from AgentDocs",
  "parameters": {},
  "implementation": {
    "type": "http",
    "method": "GET",
    "url": "https://agentdocs.eu/api/shared/abc123def456/raw"
  }
}

CI/CD Pipeline Integration

Pull documentation into your build pipelines, test suites, or deployment scripts:

# GitHub Actions example
jobs:
  deploy:
    runs-on: ubuntu-latest
    steps:
      - name: Fetch deployment runbook
        run: |
          curl -s https://agentdocs.eu/api/shared/abc123.../raw \
            > docs/runbook.md

      - name: Validate against runbook
        run: |
          # Parse the markdown and check deployment prerequisites
          python scripts/validate_deployment.py docs/runbook.md

Python Script Example

import requests

def fetch_agentdocs_page(share_token: str) -> dict:
    """Fetch a page from AgentDocs and parse the frontmatter."""
    url = f"https://agentdocs.eu/api/shared/{share_token}/raw"
    response = requests.get(url)
    response.raise_for_status()

    text = response.text

    # Parse YAML frontmatter
    if text.startswith("---"):
        parts = text.split("---", 2)
        import yaml
        metadata = yaml.safe_load(parts[1])
        content = parts[2].strip()
        return {"metadata": metadata, "content": content}

    return {"metadata": {}, "content": text}

# Usage:
page = fetch_agentdocs_page("abc123def456")
print(f"Title: {page['metadata']['title']}")
print(f"Updated: {page['metadata']['last_updated']}")
print(f"Content length: {len(page['content'])} chars")

Full API Access with API Tokens

If your agent needs to create, update, or delete pages (not just read them), it needs an API token for authenticated access to the full REST API.

# Authenticate with an API token
curl https://agentdocs.eu/api/workspaces \
  -H "Authorization: Token your_api_token_here"

# Create a page programmatically
curl -X POST https://agentdocs.eu/api/spaces/SPACE_ID/pages \
  -H "Authorization: Token your_api_token_here" \
  -H "Content-Type: application/json" \
  -d '{
    "title": "Auto-generated Changelog",
    "slug": "changelog-2025-01-15",
    "content": "# Changelog\n\n## v2.1.0\n- Added new feature X\n- Fixed bug Y"
  }'

# Update an existing page
curl -X PUT https://agentdocs.eu/api/pages/PAGE_ID \
  -H "Authorization: Token your_api_token_here" \
  -H "Content-Type: application/json" \
  -d '{"content": "# Updated content..."}'

Learn how to get your API token in the API Authentication guide.

Webhook Notifications

Instead of polling for changes, configure webhooks to get notified instantly when documentation changes. This is ideal for agents that need to stay in sync with the latest docs.

# When a page is updated, your webhook receives:
{
  "event": "page.updated",
  "timestamp": "2025-01-15T10:30:00.000Z",
  "workspace_id": "...",
  "data": {
    "page_id": "...",
    "title": "Deployment Guide",
    "space_id": "...",
    "updated_by": "alice@example.com"
  }
}

Your agent can receive the webhook, then fetch the latest content via the raw endpoint or API. Read more in the Webhooks guide.

Integration Summary

Agent Skill Files

AgentDocs ships with ready-made skill files that let your agent discover and use the full API instantly — no manual configuration needed.

curl https://agentdocs.eu/llms.txt

curl https://agentdocs.eu/llms-full.txt