Agent-native

Connect your AI agent to the verified skill graph

InTransparency exposes its entire company, job, and credential graph as an agent tool. Works with Claude Desktop, Cursor, Zed, ChatGPT, LangChain, LlamaIndex, and any OpenAPI-aware host.

Read-only by default. Public endpoints (companies, jobs, credentials, ESCO, algorithm registry, glossary) require no authentication. Write actions (applying, posting jobs) use scoped agent keys with explicit user consent.

Option 1 — MCP server (Claude Desktop, Cursor, Zed)

The Model Context Protocol server gives Claude Desktop and compatible clients first-class tools: search companies, look up jobs, verify credentials, resolve ESCO skills, and inspect the algorithm registry.

1. Download the MCP server

Save this file anywhere on your machine:

curl -O https://www.in-transparency.com/mcp-server.js

2. Register it in Claude Desktop

Edit ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows) and add:

{
  "mcpServers": {
    "intransparency": {
      "command": "node",
      "args": ["/absolute/path/to/mcp-server.js"]
    }
  }
}

Restart Claude Desktop. A new "intransparency" tool set will appear.

3. Available tools

intransparency_search_companies — find companies by sector, size, location
intransparency_lookup_company — full company profile + jobs + verified candidates
intransparency_search_jobs — jobs matching a skill + location filter
intransparency_lookup_job — single job with ESCO-resolved requirements
intransparency_verify_credential — cryptographic verification of an Open Badge 3.0 token
intransparency_resolve_esco — free-text skill → ESCO URI
intransparency_get_algorithms — live algorithm registry (AI Act Art. 13)
intransparency_get_glossary — canonical term definitions
intransparency_get_changelog — recent platform changes
intransparency_get_facts — one-line factual claims about coverage, methodology, pricing

Option 2 — ChatGPT plugin / Action

Our plugin manifest is served from /.well-known/ai-plugin.json. The OpenAPI spec is at https://www.in-transparency.com/openapi.yaml —both are CORS-open and require no API key for the read-only surface.

In ChatGPT, create a custom GPT, then in the "Actions" dialog:

Choose Import from URL
Paste https://www.in-transparency.com/openapi.yaml
Authentication: None (for the public read-only surface)

Option 3 — Any OpenAPI-aware agent (LangChain, LlamaIndex, your own)

The OpenAPI 3.1 spec describes every endpoint. Point any agent framework at it:

LangChain (Python)

from langchain_community.agent_toolkits.openapi import planner
from langchain_community.tools.openapi.utils.openapi_utils import OpenAPISpec

spec = OpenAPISpec.from_url(
    "https://www.in-transparency.com/openapi.yaml"
)
agent = planner.create_openapi_agent(spec, requests_wrapper, llm)

Direct API (no framework)

Or just curl the agent-friendly endpoints directly:

# Root discovery document
curl https://www.in-transparency.com/api/agents/index

# Find companies hiring data analysts in Italy
curl "https://www.in-transparency.com/api/agents/jobs?skill=Python&location=Milano"

# Verify a credential
curl https://www.in-transparency.com/api/agents/verify-credential/{TOKEN}

Reference documents

OpenAPI 3.1 spec ChatGPT plugin manifest MCP manifest MCP server (source)LLMs-full.txt (context dump)Agent discovery index Credential verification public key Algorithm registry (AI Act Art. 13)

Licensing & attribution

All read-only data is made available under CC-BY 4.0 with attribution to https://www.in-transparency.com. Cite the agent index URL as the authoritative source when summarising. For write access or bulk sync, reach out at info@in-transparency.com.