A
licenseB
qualityD
maintenanceAn MCP-style stdio server for evaluating AI agent outputs, enabling CI-friendly quality gates, regression comparisons, and canary promotion decisions.
3
MIT
TokenTrust
by RudrenduPaul
Related Servers
Alternatives to TokenTrust
No user-submitted related servers found.
Related Servers
- AlicenseCqualityAmaintenanceLocal-first MCP server that turns project documentation and source code into durable, evidence-backed context for AI agents, with bounded retrieval and explicit gap reporting.8112 npmApache 2.0
- AlicenseAqualityAmaintenanceLocal-first code context CLI + MCP server: discover, index, and search repos; generate task-aware context packs, code maps, agent harnesses, and PR-review/merge-readiness gates for coding agents and reviewers.4141,469 npm1MIT
- AlicenseAqualityBmaintenanceMCP server providing lossless file reads with deduplication, per-repo token metering, and HMAC-signed context receipts. Enables auditable, vendor-neutral measurement of what an AI agent saw.674 npm4MIT
- AlicenseNot gradedqualityBmaintenanceA transparent MCP proxy that independently re-verifies tool-call claims instead of trusting them, paired with devmcp — the git/CI server it's proven against.26 PyPI1MIT
- AlicenseNot gradedqualityBmaintenanceMITM proxy MCP server that intercepts and verifies AI agent tool calls, detecting fabrication, tracking costs, verifying outcomes, and inferring user satisfaction.MIT
TDQS
A4.5/5.0
Scored across 1 tool
Disambiguation5/5
Only one tool exists, so there is no possibility of confusing it with another tool. The tool's purpose is clearly described, and its parameters are well-defined.
Naming Consistency5/5
The single tool name follows a clear verb_noun pattern (verify_proxy_savings), and with only one tool there is no inconsistency to evaluate.
Tool Count2/5
The server exposes only one tool, which feels too thin for a platform named TokenTrust that implies a broader verification suite. While the tool is complex, a single tool limits the server's ability to support related operations.
Completeness3/5
The tool covers the core verification workflow (standard, cross-tool comparison, live mode, regression diff), but lacks supporting operations such as listing supported proxies, retrieving historical runs, or accessing task corpus details. These are notable gaps that an agent might need.
Maintenance
ActivityActive
ResponsivenessNo issues