Saina MCP
Server Details
Run Saina decision endpoints and retrieve decisions via MCP.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-03-26
- URL
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 2 tools
The two tools occupy clearly separate roles: get_discovery is a capability/introspection call, while search is a data-retrieval call over collections, datasets, records, and providers. There is no realistic scenario where an agent could confuse one for the other.
get_discovery follows a clean verb_noun pattern and search is a well-understood bare verb. The styles differ slightly (prefixed vs. bare verb), but both are readable and idiomatic, so it's a minor deviation rather than an inconsistency.
Two tools is very thin for a server that exposes a multi-tenant data platform spanning collections, datasets, records, and providers. The pair is well-scoped and non-redundant, but it sits at the borderline where the surface feels minimal for the apparent scope.
Discovery plus search covers orientation and retrieval, which is a reasonable read-only core, but there is no way to fetch a specific record by ID, enumerate a single collection's schema, or inspect provider model details beyond what search returns. Agents hitting a truncating search result have no clear follow-up path.
Publisher details
- Operator
- Saina
- Operator website
- https://saina.run
- Vendor relationship
- First-party
- Documentation
- https://saina.run/studio/#mcp
- Privacy policy
- Not provided
- Trust center
- Unknown
- Restrictions
- Free tier available
Available Tools
2 toolsget_discoveryGet discoveryARead-onlyInspect
List what this account can call: Saina models and connected providers with their models. Each section only shows what the connection may read.
Inputs: no named parameters.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Company resolution and enrichment with decision receipts, as a remote MCP server.
Discover MCP endpoints for real-world entities by resolving business domains.
Evidence-linked MCP selection and non-executing Safe-Call review; surfaces unknowns.
Hosted MCP for denial, prior auth, reimbursement, workflow validation, batch scoring, and feedback.
Related MCP Servers
- AlicenseNot gradedqualityAmaintenanceExposes three decision tools over MCP stdio that return typed judgments — yes/no, choice, and score — with calibrated probabilities instead of prose. Runs on an offline mock unless a live provider credential is supplied, with a per-feature egress report printed to stderr.66 npmApache 2.0
- AlicenseAqualityDmaintenanceMCP server for verifying high-impact decisions with Trust OS.2MIT
- AlicenseNot gradedqualityCmaintenanceEnables MCP clients to perform local, typed decision workflows with Ollama and Tev1, including classification/scoring, request routing, preflight checks, workflow execution, and health checks through five read-only tools.MIT
- AlicenseAqualityCmaintenanceAn MCP server that answers typed noul/choice/score questions about a given state with probability distributions and confidence, for routing, escalation, and gating decisions. It runs on pluggable backends (local Needle 3 or Laya models, or any OpenAI-compatible endpoint) and logs every decision so recorded ground truth can be used to track calibration.3MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.