similarity-search-api-sdk
Server Details
Stateless NMI + cosine fusion with entropy-driven alpha calibration
The last two health checks of this connector failed. If this server requires authentication, missing or expired test credentials may be the cause. A test profile lets Glama authenticate for health checks and discover tools; it is separate from your personal connections.
If you are the author, claim ownership, then add or update a test profile under Admin → Test Profile.
- Status
- Unhealthy
- Uptime
- 0.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP
- URL
- Repository
- nexus-mcp-infra/similarity-search-api-sdk
- GitHub Stars
- 0
- Server Listing
- Similarity Search MCP Server
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 3 tools
Each tool targets a distinct operation: corpus-level entropy estimation, full-corpus ranking fusion, and single-pair scoring. The descriptions clearly separate use cases (preflight inspection, batch ranking, explainability/debugging), so there is no overlap to confuse an agent.
All three tools share the consistent 'nexus_similarity_search_api' prefix and then follow a verb-noun pattern: estimate_corpus_entropy_profile, rank_items_by_nmi_cosine_fusion, score_pair_nmi_cosine. The naming style is also uniformly snake_case and predictable.
Three tools is perfectly scoped for this focused SDK: one for preflight entropy estimation, one for batch ranking, and one for single-pair validation. Each tool has a clear, non-redundant role, and the count fits the server's narrow purpose.
The tool surface covers the full workflow for a stateless similarity search: inspect corpus entropy/alpha before running, rank all items via NMI-cosine fusion, and validate/debug individual pair scores. There are no obvious dead ends or missing lifecycle steps in this domain.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Authenticated Multi-LLM Agent
KYA agent identity verification and trust scoring for autonomous A2A networks
On-device human sensing for AI: EDNA ID continuity and live human context via MCP.
Zero-knowledge attestation for agent capability and trust score claims
Related MCP Servers
- AlicenseNot gradedqualityBmaintenanceEnables real-time fusion of 2D/3D visual bounding boxes, head-pose gaze vectors, and acoustic beamforming azimuth angles into cross-modal focal salience scores to resolve deictic spatial references for multimodal agents.7MIT
- AlicenseNot gradedqualityNot gradedmaintenanceEnables AI agents to fuse 2D/3D visual bounding boxes, user head-pose gaze vectors, and acoustic beamforming azimuth angles into cross-modal focal salience scores. It also resolves deictic spatial references in real time, running as a zero-dependency Python MCP server over JSON-RPC stdio.MIT
- FlicenseNot gradedqualityCmaintenanceOn-device behavioral-biometric human sensing for AI: 16 channels (keystroke timing, pointer curvature, scroll pauses, device motion, typing bursts) scored locally into a live human-confidence vector; MCP tools for human proof, signal vector and human context. Zero raw biometrics leave the device - hash patterns only.-
- FlicenseNot gradedqualityNot gradedmaintenanceEnables detecting LLM hallucinations and confabulations by clustering sampled responses into semantic equivalence classes and computing semantic entropy.-
Glama MCP Gateway
Add one secure layer between your agents and this server.