What this kind of tool is for
- Hand your agent a structured way to call a model or an inference API.
- Compare outputs from two different providers on the same prompt.
- Wire retrieval, embeddings, or generation into an existing agent workflow.
How to compare servers like this
- Provider coverage:
- Match the tool's supported providers and models to the ones your project uses.
- Cost exposure:
- Model-backed tools spend real API budget; check how usage and limits are configured.
- Maintenance signal:
- The provider landscape shifts weekly; prefer tools updated within the last few months.
- Config surface:
- Prefer tools whose environment-variable or config keys are documented plainly.
This page carries your copy-paste config: pick your MCP client in the install section on this page and use the copy button.
What is the io.github.l-agence/agence MCP server?
AI governance MCP server — policy enforcement, skills, memory, multi-LLM consensus
How to install io.github.l-agence/agence
Copy-paste configuration for popular MCP clients.
AGENCE_ROOTPath to agence installation root (auto-detected if installed via npm)
{
"mcpServers": {
"agence": {
"command": "npx",
"args": [
"-y",
"@l-agence/mcp-server-agence"
],
"env": {
"AGENCE_ROOT": "<YOUR_AGENCE_ROOT>"
}
}
}
}Related MCP servers

io.github.l33tdawg/sage
Persistent, consensus-validated institutional memory for AI agents with Byzantine-resilient infrastructure.

Banyan Memory
Persistent, governed local memory for MCP-compatible AI clients.

Local LLM cost proxy: forecasts each call and recommends the cheapest model that clears the task.

Sophon
Honest token economics for MCP agents. 68% tokens saved, zero-ML Rust binary.

BLACKPROOF Local MCP
Local-first cyber evidence integrity checks and dossier comparison for audits and reviews.

MCP Server that turns your AI agent into a localization expert with token-efficient i18n translation