infocepo-infra-mcp
Exposes infocepo.com infrastructure (LLM, ChromaDB, S3, Docker registry, service discovery) as MCP tools for AI agents.
README
infocepo-infra-mcp
MCP server qui expose l'infrastructure infocepo.com comme outils MCP standard.
Installation
cd infocepo-infra-mcp
python3 -m venv .venv
source .venv/bin/activate
pip install -e .
Configuration
Créer ~/.infocepo-credentials (format JSON) :
{
"api_key": "sk-...",
"chroma_token": "CHROMA_TOKEN",
"s3_access_key": "AKIA...",
"s3_secret_key": "secret_key_here",
"registry_user": "user",
"registry_password": "REG_PASSWORD"
}
Variables d'environnement (alternative au fichier) :
export INFOCEPO_API_KEY=sk-...
export INFOCEPO_CHROMA_TOKEN=...
export INFOCEPO_S3_ACCESS_KEY=AKIA...
export INFOCEPO_S3_SECRET_KEY=...
export INFOCEPO_REGISTRY_PASSWORD=...
export INFOCEPO_CREDENTIALS_FILE=/path/to/credentials.json
Configuration MCP client
Pour Hermes (config.yaml) :
mcp_servers:
infocepo-infra:
command: /home/ai-agent/work/infocepo-infra-mcp/.venv/bin/python
args:
- -m
- infocepo_mcp.server
env:
PYTHONPATH: /home/ai-agent/work/infocepo-infra-mcp/src
INFOCEPO_API_KEY: sk-...
timeout: 60
Outils disponibles
Services API
| Tool | Description |
|---|---|
llm_chat |
Chat completions OpenAI-compatible (ai-default, ai-thinking, ai-fast, etc.) |
llm_vision |
OCR / VLM — image (URL ou base64) → description |
stt_transcribe |
Transcription audio → texte (whisper-1) |
tts_speech |
Synthèse vocale texte → audio (opus/wav/mp3) |
image_generate |
Génération d'images (OpenDalle) |
embeddings_create |
Text embeddings (bge-m3) pour RAG/search |
summary_text |
Résumé de longs textes |
diarize_audio |
Segmentation locuteurs audio |
ChromaDB
| Tool | Description |
|---|---|
chromadb_collections |
Lister collections |
chromadb_search |
Recherche vectorielle (auto-embed) |
chromadb_upsert |
Ajouter des documents vectorisés |
Registry & S3
| Tool | Description |
|---|---|
registry_list |
Lister images Docker du registry privé |
s3_list |
Lister objets dans un bucket S3 |
s3_upload |
Upload fichier vers S3 |
s3_download |
Download fichier depuis S3 |
Discovery (auto-wiki)
| Tool | Description |
|---|---|
infra_list_services |
Lister tous les services découverts |
infra_refresh_discovery |
Re-fetch wiki et redécouvrir |
infra_read_wiki |
Lire une page wiki |
infra_parse_wiki |
Parser une page wiki en sections structurées |
Test
python -m pytest tests/ -v # Tests unitaires
TEST_LIVE=1 python -m pytest tests/ -v # Tests live (nécessite réseau)
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.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
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.