MCP Server
MCP
io.github.TheAiSingularity/agentic-research
By Local research agent that verifies its own answers. Runs on Gemma 3 4B + Ollama, $0/query.
Install
uvx agentic-research-engineConfiguration Example
{
"remotes": [],
"packages": [
{
"registryType": "pypi",
"identifier": "agentic-research-engine",
"version": "0.1.3",
"runtimeHint": "agentic-research-mcp",
"transport": {
"type": "stdio"
},
"environmentVariables": [
{
"description": "Any OpenAI-compatible endpoint. Default: OpenAI cloud. Use http://localhost:11434/v1 for Ollama.",
"name": "OPENAI_BASE_URL"
},
{
"description": "API key for the endpoint above. Use 'ollama' as a sentinel value when running locally against Ollama.",
"isSecret": true,
"name": "OPENAI_API_KEY"
},
{
"description": "Model identifier used for the synthesize node. Defaults to 'gpt-5-mini'; set to 'gemma3:4b' for Mac-local Ollama.",
"name": "MODEL_SYNTHESIZER"
},
{
"description": "Model for the plan / classify / critic / compress / verify nodes. Defaults to 'gpt-5-nano'.",
"name": "MODEL_PLANNER"
},
{
"description": "Embedding model identifier (for retrieval + memory). Default 'text-embedding-3-small'; use 'nomic-embed-text' on Ollama.",
"name": "EMBED_MODEL"
},
{
"description": "Base URL of the SearXNG meta-search instance. Default http://localhost:8888.",
"name": "SEARXNG_URL"
},
{
"description": "Path to an index directory built via scripts/index_corpus.py. When set, local corpus hits augment web search.",
"name": "LOCAL_CORPUS_PATH"
},
{
"description": "Set to '1' to enable the BAAI/bge-reranker-v2-m3 cross-encoder rerank stage. First run downloads ~560MB.",
"name": "ENABLE_RERANK"
},
{
"description": "Set to '0' to skip the trafilatura full-page fetch stage. Default '1'.",
"name": "ENABLE_FETCH"
}
]
}
]
}
mcp
model-context-protocol
pypi
Comments
Sign in to leave a comment