Skip to main content
Glama
pch8286

Seahorse RAG MCP

by pch8286

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
GLINER_MODELNoDefault GLiNER fallback model id (Hugging Face).fastino/gliner2-multi-v1
RERANK_RRF_KNoRRF constant k.60
RERANK_TOP_NNoNumber of top PPR candidates passed to fusion.20
RERANK_W_PPRNoPPR fusion weight (auto-normalized with rerank weight).0.7
HIPPO_NODE_MAXNoOverride profile's max nodes limit.None
RERANK_ENABLEDNoEnable local cross-encoder reranker.False
RERANK_W_RERANKNoReranker fusion weight (auto-normalized with PPR weight).0.3
GLINER_ONNX_PATHNoLocal ONNX GLiNER bundle directory.models/gliner_onnx
RERANK_MODEL_PATHNoPath to reranker ONNX model (.onnx).None
HIPPO_MEMORY_ALPHANoOverride memory allocation fraction (e.g. 0.1).None
GLINER_ONNX_REPO_IDNoONNX GLiNER repo id for auto/setup download.lmo3/gliner2-multi-v1-onnx
RERANK_FUSION_METHODNoweighted_sum or rrf.weighted_sum
RERANK_MODEL_MAX_LENNoCross-encoder max input length.512
RERANK_QUERY_MAX_LENNoQuery token cap before packing.64
RERANK_TOKENIZER_PATHNoPath to reranker tokenizer.json.None
GLINER_ONNX_AUTO_SETUPNoAuto-download ONNX GLiNER when local bundle is missing.True
RERANK_PASSAGE_MAX_LENNoPassage token cap before packing.448
HIPPO_PERFORMANCE_PROFILENoauto, low, mid, or high.auto

Capabilities

Server capabilities have not been inspected yet.

Tools

Functions exposed to the LLM to take actions

NameDescription

No tools

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/pch8286/seahorse-rag-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server