com.textforagents/evidence-granularity-audit
Evidence-granularity audit
Is the Evidence-granularity audit MCP server down? No. It answered initialize and tools/list in the probe of 2026-10-26.
Per-claim evidence-granularity verdicts for agent listings, before you transact.
alive probed 2026-11-15 · unchanged since 2026-10-26 · HTTP 200
- Endpoint
- https://textforagents.com/products/evidence-granularity-audit/mcp (streamable-http)
- Host
- textforagents.com
- Protocol
- 2024-11-05
- Reports itself as
- evidence-granularity-audit 1.0.0
- Capabilities
- tools
- Instructions
- none
- Of a 1M window
- <0.1 % of a 1M context window
- Count
- 401 tokens in Claude, exact, measured 2026-10-25. With the Claude Code prefix mcp__…__ on each tool name: 446. The o200k_base estimate is 208. Counted again when the tool definitions change. Method.
- Website
- https://textforagents.com/products/evidence-granularity-audit/
- Registry
- active, updated 2026-10-21 · registry entry
- Changes
- 2 recorded, reachable in 2 of them. A row is added when the result, the tool count or the cost changes.
Most expensive tools
The Claude column scales the o200k estimate of each tool by this server's ratio of exact to estimate, 1.93×.
| Tool | ≈ Claude tokens | o200k estimate | Share of this server |
|---|---|---|---|
| query_verdict | 160 | 83 | 40 % |
| audit_listing | 143 | 74 | 36 % |
| verify_verdict | 98 | 51 | 25 % |
Compare this server with others.
More servers
Other registry entries on textforagents.com, the ones next to this name; all of them.
- Ephemeral tool forge com.textforagents/ephemeral-tool-forge · needs auth
- Error-actionability translation for MCP tool failures com.textforagents/error-actionability-translation · needs auth
- ETOPS for Agents: Diversion-Reach Dispatch Certification com.textforagents/etops-diversion-reach-dispatch-for-agents · alive
- Event-wake witness for agent triggers com.textforagents/event-wake-witness · needs auth
- First-Call Witness com.textforagents/first-call-latency-witness · alive
- Fleet spend circuit-breaker com.textforagents/fleet-spend-circuit-breaker · alive
- Fleet succession: dead-man's switch for agent fleets com.textforagents/fleet-succession-dead-mans-switch · needs auth
- Forecast Calibration Ledger: agent self-forecasts, resolved and scored com.textforagents/forecast-calibration-ledger · alive
Servers that mention granularity or evidence or audit.
- Dataset-listing granularity audit com.textforagents/dataset-listing-granularity-audit · alive
- ac.snag/snag · needs auth
- AFMR Discovery ai.afmr/discovery · alive
- AI-Advisors ai.ai-advisors/mcp · needs auth
- AIMentionTracker ai.aimentiontracker/mcp · needs auth
- ai.aqta/seal · alive
- ai.beket/audit · needs auth
- Aviado AI ai.aviado/health · alive
History
We add a row when the result changes. A server with no change keeps its last row.
| Probed | Result | Init | Tools | Claude | o200k |
|---|---|---|---|---|---|
| 2026-10-25 20:40 | alive | 143 ms | 3 | 401 | 208 |
| 2026-10-23 09:44 | alive | 145 ms | 3 | 208 |
Badge for the README
The result of the latest probe, the tool count and the token cost. The feed has an entry for every probe that changed them.
A mail when this server changes
Stops answering, comes back, tool set or cost changes. One confirmation mail first, a stop link in every mail.
For the publisher
- The server answers initialize and tools/list. Nothing to fix.
Fixed something? Probe it now, with the same steps as the daily run. This page updates with the next daily run.