mcpField
A
agent-foundry

agent-foundry

Local
github.com/youcislaAI & Agents
Repository

About agent-foundry

Agent Foundry is a local skill and agent runtime for AI coding assistants, with a catalog of skills and agents plus a daemon that plans, executes, and verifies tasks. It offers CLI and stdio MCP access, and stores execution data locally.

Key features

  1. 01Skill catalog and ranking
  2. 02Plan, execute, and verify tasks
  3. 03Agent dispatch and orchestration
  4. 04Local daemon and execution logs
  5. 05Paired skill evaluation

Use cases

  1. 01Select skills for a coding request
  2. 02Run a task through a skill and verify output
  3. 03Compare task results with and without a skill

MCP support

Its stdio MCP server exposes planning, execution, skill listing and search, verification, action checks, runtime status, execution history, and model listing.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "youcisla-agent-foundry": {
      "command": "uvx",
      "args": [
        "agent-foundry-runtime"
      ]
    }
  }
}
Run commanduvx agent-foundry-runtime

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
pypiagent-foundry-runtime0.4.2

Tools

4

Saved tool list · updated 1w ago

ParameterTypeRequiredDescription
promptstringYes
max_resultsintegerNo

Details

The maintainer has not added details yet. Check the README in the repository.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.