Trust Live
Server Details
Evidence-linked MCP selection and non-executing Safe-Call review; surfaces unknowns.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 5 tools
Each tool has a distinct primary target (provider profile, capability-by-action-ID, comparison, recommendation, safe-call evaluation). However get_provider_profile and get_capability both surface capability/evidence data, and compare_providers vs recommend_provider overlap in provider-selection intent, so an agent could occasionally hesitate.
All tool names follow a consistent snake_case verb_noun/verb_object pattern (compare_providers, get_capability, get_provider_profile, recommend_provider, evaluate_safe_call). No mixing of conventions or casing styles.
Five tools is well-scoped for a provider-trust service, covering profile lookup, capability lookup, comparison, recommendation, and safety evaluation without redundancy or thinness.
The surface covers the core read workflows of the domain: inspect a provider, inspect a capability, compare, recommend, and evaluate Safe-Call constraints. Minor gaps exist, such as listing/discovering all providers or capabilities, but agents can work around these.
Publisher details
- Operator
- ChanghuLiu (Agent Trust Lab) · Publisher source
- Operator website
- https://agenttrustlab.com · Publisher source
- Vendor relationship
- First-party · Publisher source
- Documentation
- https://github.com/ChanghuLiu/mcp-selection-lab/blob/main/docs/trust-live-decision-core-v0.1.md · Publisher source
- Privacy policy
- Not provided
- Trust center
- Not available
- Restrictions
- Trust Live exposes five read-only tools for provider and capability lookup, recommendations, comparisons, and Safe-Call preflight. Safe-Call evaluates a proposed call only: it does not contact providers, execute tools, or authorize execution. The GitHub profile remains REVIEW_REQUIRED. Deployment-to-source mapping and remote data retention/logging remain unverified; other evidence gaps may affect recommendations. Treat results as decision support, not an execution approval, guarantee, or security/compliance certification. · Publisher source
Available Tools
5 toolscompare_providersBRead-onlyIdempotentInspect
Compare matching providers across capability, verification, safety, payment, freshness and unknowns.
Inputs: task_requirements (required). Returns: object
evaluate_safe_callBRead-onlyIdempotentInspect
Evaluate Safe-Call constraints without invoking the provider tool.
Inputs: arguments (required), provider_id (required), capability_id (required), data_classes, +2 more. Returns: object
get_capabilityBRead-onlyIdempotentInspect
Get every provider capability with this canonical action ID, including evidence and Safe-Call contract.
Inputs: capability_id (required). Returns: object
get_provider_profileBRead-onlyIdempotentInspect
Get a canonical provider profile with capabilities, evidence references, and safe-call contracts.
Inputs: provider_id (required). Returns: object
recommend_providerBRead-onlyIdempotentInspect
Recommend a provider with hard-filter outcomes, component scores, evidence, and Safe-Call constraints.
Inputs: task_requirements (required). Returns: object
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
SaSame GEC public MCP for discovering OPEN outcome work and supporting evidence.
Remote MCP for A2A failure replay MCP, structured receipts, audit logs, and reviewer-ready evidence.
Remote MCP for C2PA intake verifier MCP, structured receipts, audit logs, and reviewer-ready evidenc
The evidence layer for MCP: live operational grades plus Trust Receipts for every registry server.
Related MCP Servers
- AlicenseAqualityBmaintenanceEnables customer-success teams and AI hosts to inspect account evidence, assess onboarding readiness, assemble unsent bilingual follow-up drafts, and prepare traceable technical handoffs through scoped MCP tools. It preserves source references and distinguishes recorded failures, missing evidence, and possible explanations for human review.8MIT
- AlicenseBqualityBmaintenanceEnables coding assistants to gather bounded source evidence, prepare typed judgments, and verify claims through MCP tools while leaving editing and execution to the host.13MIT
- AlicenseAqualityBmaintenanceA local-first MCP server for retrieving a small evidence set and recording reviewed conclusions, policy-gated and redacted without giving an agent general filesystem access.5MIT
- FlicenseNot gradedqualityCmaintenanceEnables users to check whether procedures are current and whether actions have the stored evidence needed for human review, returning status, citations, and blockers through read-only MCP tools while always requiring human review.-
Glama MCP Gateway
Add one secure layer between your agents and this server.