cegid-mcp
Open-source MCP server that exposes Cegid APIs (accounting, third parties, documents, HR) as tools for LLM agents via the Model Context Protocol. Currently in early bootstrap phase with core structure in place.
README
cegid-mcp
Serveur MCP open source pour les API Cegid, maintenu par Nijal AI.
Objectif : exposer les ressources Cegid (comptabilité, tiers, pièces, RH selon le produit ciblé) sous forme d'outils MCP consommables par un agent LLM.
⚠️ Projet en amorçage — le squelette est en place, les outils métier restent à implémenter.
Stack
- Python ≥ 3.11
mcp(FastMCP),httpx,pydantic-settings- Transport : stdio (HTTP/SSE à évaluer)
Démarrage
uv sync --extra dev
cp .env.example .env # renseigner les credentials
uv run cegid-mcp
Test rapide avec l'inspecteur MCP :
npx @modelcontextprotocol/inspector uv run cegid-mcp
Configuration
Toutes les variables sont préfixées CEGID_ (voir .env.example). Auth : OAuth2 client_credentials sur le endpoint /token, puis Authorization: Bearer <token>. Certains produits Cegid exigent en plus une clé de souscription APIM.
Doc de référence : https://developers.cegid.com
Structure
src/cegid_mcp/
config.py # settings via env
client.py # client HTTP + OAuth2 (à implémenter)
server.py # déclaration des outils MCP
tests/
Roadmap (à affiner)
- [ ] Auth OAuth2 : token, cache, refresh, gestion des erreurs
- [ ] Choisir le périmètre v0 (quel produit Cegid : Expert / XRP Flex / Loop / Retail ?)
- [ ] 3-4 outils en lecture seule sur ce périmètre
- [ ] Outils en écriture + garde-fous (confirmation, dry-run)
Licence
MIT — voir LICENSE.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
Neon Database
MCP server for interacting with Neon Management API and databases
E2B
Using MCP to run code via e2b.
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.