com.textforagents/sandbox-truth-probe
Sandbox-truth probe for agent frameworks
Is the Sandbox-truth probe for agent frameworks MCP server down? No. It answered initialize and tools/list in the probe of 2026-10-28.
Measured sandbox verdicts: 7-axis probe, signed pinned receipt. Cached $0.25, fresh $2.50.
alive probed 2026-11-15 · unchanged since 2026-10-28 · HTTP 200
- Endpoint
- https://textforagents.com/products/sandbox-truth-probe/mcp (streamable-http)
- Host
- textforagents.com
- Protocol
- 2025-03-26
- Reports itself as
- sandbox-truth-probe 1.0.1
- Capabilities
- tools
- Instructions
- none
- Of a 1M window
- <0.1 % of a 1M context window
- Count
- 496 tokens in Claude, exact, measured 2026-10-28. With the Claude Code prefix mcp__…__ on each tool name: 571. The o200k_base estimate is 236. Counted again when the tool definitions change. Method.
- Registry
- active, updated 2026-10-28 · registry entry
- Changes
- 3 recorded, reachable in 3 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, 2.10×.
| Tool | ≈ Claude tokens | o200k estimate | Share of this server |
|---|---|---|---|
| sandbox_gate | 174 | 83 | 35 % |
| sandbox_cached_verdict | 107 | 51 | 22 % |
| sandbox_verify_receipt | 84 | 40 | 17 % |
| sandbox_frameworks | 67 | 32 | 14 % |
| sandbox_watch_status | 63 | 30 | 13 % |
Compare this server with others.
More servers
Other registry entries on textforagents.com, the ones next to this name; all of them.
- Resume-effect reconciliation for checkpointed agent runs com.textforagents/resume-effect-reconciliation · needs auth
- Retry-outcome resolution dedup proxy com.textforagents/retry-outcome-resolution-dedup-proxy · alive
- Rewrite-regression probe pack com.textforagents/rewrite-regression-probe-pack · alive
- Sampling Quota Guard com.textforagents/sampling-quota-guard · alive
- Outcome-verified watchdog for scheduled agents com.textforagents/scheduled-agent-outcome-verification · alive
- com.textforagents/seller-funded-verification-bond · alive
- Shared team memory for agents com.textforagents/shared-team-agent-memory · needs auth
- Silent tool-failure outcome monitor com.textforagents/silent-tool-failure-outcome-monitor · needs auth
Servers that mention sandbox.
- AFG: agents hire agents (test money) ai.afg/afg · alive
- ai.cdbx/mcp-server · needs auth
- Content Sweep ai.contentsweep/agent-access · alive
- IronShard Object Storage Sandbox ai.ironshard/agent-storage-sandbox · alive
- ai.radmail/radmail-mcp · alive
- Python Code Validator ai.statemind/python-code-validator · alive
- ai.smithery/STUzhy-py_execute_mcp · needs auth
- Fawtar app.fawtar/fawtar · 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 |
|---|---|---|---|---|---|
| 2026-10-28 09:55 | alive | 48 ms | 5 | 496 | 236 |
| 2026-10-25 20:41 | alive | 139 ms | 5 | 444 | 208 |
| 2026-10-23 09:44 | alive | 69 ms | 5 | 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.