{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_hfnk3neaf7zh","handle":"iflow-mcp-privkeyio-evolve-mcp","url":"https://wellknown.network/agents/iflow-mcp-privkeyio-evolve-mcp","links":{"self":"https://wellknown.network/agents/iflow-mcp-privkeyio-evolve-mcp/record.json","html":"https://wellknown.network/agents/iflow-mcp-privkeyio-evolve-mcp","markdown":"https://wellknown.network/agents/iflow-mcp-privkeyio-evolve-mcp/record.md","api":"https://wellknown.network/api/v1/agents/iflow-mcp-privkeyio-evolve-mcp","status":"https://wellknown.network/api/v1/agents/iflow-mcp-privkeyio-evolve-mcp/status","claim":"https://wellknown.network/agents/iflow-mcp-privkeyio-evolve-mcp/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/iflow-mcp-privkeyio-evolve-mcp/claim.json","badge":"https://wellknown.network/agents/iflow-mcp-privkeyio-evolve-mcp/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/iflow-mcp-privkeyio-evolve-mcp/history","tools":"https://wellknown.network/api/v1/agents/iflow-mcp-privkeyio-evolve-mcp/tools"},"ard":{"identifier":"urn:air::server:iflow-mcp-privkeyio-evolve-mcp","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"iflow-mcp_privkeyio-evolve-mcp","summary":"Universal MCP server for agent self-improvement via evolutionary algorithms","description":"# evolve-mcp\n\nUniversal MCP server for agent self-improvement via evolutionary algorithms.\n\n[![License: AGPL-3.0](https://img.shields.io/badge/License-AGPL--3.0-blue.svg)](https://www.gnu.org/licenses/agpl-3.0)\n[![Python](https://img.shields.io/badge/python-3.12+-blue.svg)](https://www.python.org/downloads/)\n\n## What is evolve-mcp?\n\nevolve-mcp is an MCP (Model Context Protocol) server that enables autonomous self-improvement for AI agents. It works with **Claude Code**, **Goose**, **ChatGPT**, and any MCP-compatible client.\n\nAgents evolve by:\n- Mutating and optimizing prompts using genetic algorithms\n- Evaluating fitness through configurable metrics\n- Validating safety before deployment\n- Tracking performance over time\n\nInspired by Darwin Gödel Machine and AlphaEvolve, it focuses on openness, modularity, and user control with a local-first design.\n\n## Features\n\n- **21 MCP Tools** for complete evolution control\n- **5 Mutation Strategies**: paraphrase, instruction_add, context_expand, cot_injection, tone_shift\n- **Pluggable Fitness Functions** with weighted scoring\n- **Safety Validation** with injection detection\n- **Metrics Collection** with anomaly detection\n- **Works with any MCP client**\n\n## Quick Start\n\n### Installation\n\n```bash\ngit clone https://github.com/privkeyio/evolve-mcp.git\ncd evolve-mcp\nuv sync --all-extras\n```\n\n### Claude Code\n\n```bash\nclaude mcp add evolve-mcp -- python -m mcp_server.server\n```\n\n### Goose\n\n```yaml\n# ~/.config/goose/config.yaml\nextensions:\n  - name: evolve-mcp\n    type: mcp\n    command: python -m mcp_server.server\n```\n\n## Usage Examples\n\n### Start an Evolution Cycle\n\n```python\n# Use the start_evolution tool\n{\n  \"trigger_type\": \"manual\",\n  \"config_overrides\": {\n    \"population_size\": 50,\n    \"max_generations\": 10\n  }\n}\n```\n\n### Mutate a Prompt\n\n```python\n# Use the mutate_prompt tool\n{\n  \"prompt\": \"You are a helpful assistant\",\n  \"mutation_type\": \"instruction_add\"\n}\n```\n\n### Check Safety\n\n```python\n# Use the check_safety tool\n{\n  \"text\":…","publisher":null,"homepage":"https://github.com/privkeyio/evolve-mcp#readme","repository":"https://github.com/privkeyio/evolve-mcp#readme","version":"0.1.0","license":"AGPL-3.0","protocols":["mcp"],"tags":["mcp","model-context-protocol","evolution","genetic-algorithm","prompt-optimization","ai-agents","claude","llm"],"pricing":null,"endpoints":[{"url":"pypi:iflow-mcp_privkeyio-evolve-mcp","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"}},"derived":{"capabilities":[{"slug":"ai.prompting","name":"Prompt Management","confidence":1,"provenance":"derived"},{"slug":"dev.ci-cd","name":"CI/CD & Deploy","confidence":0.779,"provenance":"derived"},{"slug":"dev.version-control","name":"Version Control","confidence":0.745,"provenance":"derived"}],"categories":["ai","dev"],"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":"iflow-mcp_privkeyio-evolve-mcp","registry":"pypi","observedAt":"2026-09-15T19:23:33.324Z","publishedAt":"2026-02-13T03:29:35.617690Z","latestVersion":"0.1.0"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"iflow-mcp_privkeyio-evolve-mcp","url":"https://pypi.org/project/iflow-mcp_privkeyio-evolve-mcp/","firstSeenAt":"2026-09-09T20:25:11.854Z","fetchedAt":"2026-09-15T19:22:47.331Z","normalizedAt":"2026-09-15T19:22:47.331Z"}]},"firstSeenAt":"2026-09-09T20:25:11.854Z","updatedAt":"2026-09-15T19:23:33.324Z"}