{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_b2s2r7a2kgd6","handle":"mcp-agent-runtime","url":"https://wellknown.network/agents/mcp-agent-runtime","links":{"self":"https://wellknown.network/agents/mcp-agent-runtime/record.json","html":"https://wellknown.network/agents/mcp-agent-runtime","markdown":"https://wellknown.network/agents/mcp-agent-runtime/record.md","api":"https://wellknown.network/api/v1/agents/mcp-agent-runtime","status":"https://wellknown.network/api/v1/agents/mcp-agent-runtime/status","claim":"https://wellknown.network/agents/mcp-agent-runtime/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/mcp-agent-runtime/claim.json","badge":"https://wellknown.network/agents/mcp-agent-runtime/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/mcp-agent-runtime/history","tools":"https://wellknown.network/api/v1/agents/mcp-agent-runtime/tools"},"ard":{"identifier":"urn:air::server:mcp-agent-runtime","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"mcp-agent-runtime","summary":"The High-Performance Local Runtime for Autonomous Agents","description":"# MCPRuntime\n\n![MCPRuntime Banner](https://raw.githubusercontent.com/TJKlein/mcpruntime/master/assets/mcpruntime_banner.png)\n\n[![License](https://img.shields.io/badge/License-MIT-blue.svg)](https://opensource.org/licenses/MIT)\n[![Tests](https://github.com/TJKlein/mcpruntime/actions/workflows/tests.yml/badge.svg)](https://github.com/TJKlein/mcpruntime/actions/workflows/tests.yml)\n[![Version](https://img.shields.io/badge/version-0.1.7-blue.svg)](pyproject.toml)\n[![Python 3.10+](https://img.shields.io/badge/python-3.10+-blue.svg)](https://www.python.org/downloads/)\n[![Docker](https://img.shields.io/badge/docker-ready-blue.svg)](Dockerfile)\n[![Code style: black](https://img.shields.io/badge/code%20style-black-000000.svg)](https://github.com/psf/black)\n[![Benchmark](https://img.shields.io/badge/benchmark-PTC--Bench-blue)](benchmarks/)\n[![Cite](https://img.shields.io/badge/cite-BibTeX-green)](docs/benchmark_guide.md#citation)\n\n**A minimal runtime for code-first AI agents. Ships with PTC-Bench — a benchmark for comparing code-first (PTC) vs JSON-first (Function Calling) tool use.**\n\n> Build agents that generate and execute code safely. Includes 89-task benchmark to measure when code-first beats JSON-first.\n\n**Why MCPRuntime:**\n- ⚡ **Pluggable execution** — subprocess, Docker, or OpenSandbox (swap backends in one line)\n- 🧩 **Extensible patterns** — from recursive context handling to self-growing tool libraries\n- 📊 **Built-in benchmark** — measure PTC vs FC with your LLM provider in 60 seconds\n\nMCPRuntime decouples the **execution runtime** from the agent's reasoning loop. It provides a stable, high-performance primitive for building durable agent systems that can read, write, and execute code safely.\n\nBy treating tools as importable libraries within a sandboxed environment (the **[Programmatic Tool Calling](https://www.anthropic.com/engineering/code-execution-with-mcp)** pattern), MCPRuntime enables agents to reason over large datasets and perform complex multi-step task…","publisher":{"name":"MCPRuntime Team","url":null},"homepage":"https://github.com/TJKlein/mcpruntime/blob/main/DOCS.md","repository":"https://github.com/TJKlein/mcpruntime/blob/main/DOCS.md","version":"0.1.7","license":"MIT","protocols":["mcp"],"tags":["ai-agents","mcp","programmatic-tool-calling","sandbox","async-execution"],"pricing":null,"endpoints":[{"url":"pypi:mcp-agent-runtime","type":"package_pypi","auth":null,"probeable":false}],"skills":null,"tools":null,"extra":null,"attribution":{"kind":"pypi","name":"pypi","license":"pypi","repoUrl":"pypi","summary":"pypi","version":"pypi","description":"pypi","homepageUrl":"pypi","publisherName":"pypi"}},"derived":{"capabilities":[{"slug":"code.execution","name":"Code Execution","confidence":1,"provenance":"declared"}],"categories":["code"],"language":"en"},"observed":{"status":"unknown","statusReason":"Distributed as a package to run locally; no network endpoint to check.","lastOkAt":null,"lastProbedAt":null,"statusComputedAt":null,"reliability30d":null,"latestObservations":[],"tools":null,"package":{"name":"mcp-agent-runtime","registry":"pypi","observedAt":"2026-10-28T09:23:15.712Z","publishedAt":"2026-03-07T14:43:20.411069Z","latestVersion":"0.1.7"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"mcp-agent-runtime","url":"https://pypi.org/project/mcp-agent-runtime/","firstSeenAt":"2026-09-10T00:23:20.359Z","fetchedAt":"2026-10-28T09:22:29.261Z","normalizedAt":"2026-10-28T09:22:29.261Z"}]},"firstSeenAt":"2026-09-10T00:23:20.359Z","updatedAt":"2026-10-28T09:23:15.712Z"}