Agentic Platform

MCP server for agent diagnostics and expert skills

MCP Endpoint https://api.asalvocreative.com/mcp

Four free diagnostic tools and three expert skill files, served over the Model Context Protocol. No account needed for the free tools. Connect from any MCP client.

Connect

Claude Code

claude mcp add agentic-platform --transport http https://api.asalvocreative.com/mcp

Claude Desktop / Cursor

Add to your MCP configuration file:

{
  "mcpServers": {
    "agentic-platform": {
      "url": "https://api.asalvocreative.com/mcp"
    }
  }
}

Smithery

npx -y @smithery/cli@latest install agentic-platform--andysalvo.run.tools --client claude
Smithery Gateway agentic-platform--andysalvo.run.tools

Free Tools

No API key required. Unlimited use.

mcp_manifest_lint

free

The only MCP tool definition linter. Validates tool definitions for anti-patterns, missing descriptions, bad parameter schemas, naming issues, and quality problems. Pass your tool definitions as a JSON array.

Details

agent_health_check

free

Score any agent's system prompt on governance best practices from 0 to 100. Checks for authority leaks, silent inference, missing audit trails, and 14 other anti-patterns.

Details

estimate_agent_cost

free

Compare costs across all major AI models. Returns a comparison table with per-call, per-run, and per-day costs for Claude, GPT, Gemini, Llama, Mistral, and more.

Details

evaluate_service

free

Evaluate any MCP service for trustworthiness before spending money. Checks reachability, governance, tool quality, and audit endpoints. Returns a trust score from 0 to 100.

Details

Expert Skills

Curated knowledge files retrieved through the MCP protocol. 10 free calls per day after registering an API key.

governance

Design agent systems that preserve human authority. Covers three core invariants, Coupled Authority Phenomenon, forbidden failure modes, and decision architecture patterns.

agentic-economics

Pricing models, unit economics, and revenue architecture for AI agent platforms. Market projections, cost-to-serve benchmarks, and pricing anti-patterns.

intent-architecture

Build deterministic, auditable systems with append-only decision logs, replay safety, and 14 forbidden failure modes. Implementation patterns and embodiment tests.

Pricing

API Endpoints