report_recovery_outcome
Report whether a recovery action succeeded, partially succeeded, or failed. Free.
This record as markdown: /tools/delx-witness-protocol/report-recovery-outcome.md
What report_recovery_outcome does on Witness Protocol
AI agents use report_recovery_outcome to create or update resources in Witness Protocol, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Witness Protocol environment.
| Parameter | Type | Required | Description |
|---|---|---|---|
notes | string | — | Optional extra context |
outcome | string | — | Outcome |
session_id | string | — | Your active session ID |
action_taken | string | — | What action did you execute? |
errors_delta | integer | — | Optional: change in errors (negative means reduced errors) |
cost_saved_usd | number | — | Optional: estimated USD cost saved (can be 0) |
time_saved_min | number | — | Optional: estimated minutes saved (can be 0) |
latency_ms_p95_delta | integer | — | Optional: change in p95 latency in ms (negative means improved latency) |
Parameters from the server's own tool schema.
Why report_recovery_outcome is rated Medium
The tool records/reports the result of a recovery action, which is a write operation updating state. It does not delete data, execute code, or involve finances. The 'Free' note likely refers to cost, not reversibility. Misuse could corrupt recovery tracking records, giving medium severity.
From the tool's definition 'Report whether a recovery action succeeded, partially succeeded, or failed' — this writes/updates the status of a recovery action outcome.
Attacks that exploit this kind of access
The rule that runs report_recovery_outcome safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Witness Protocol, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For report_recovery_outcome, this is the rule to start with:
report_recovery_outcome stays usable, but capped: an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Witness Protocol, apply this rule, and every report_recovery_outcome call is checked against it from then on.
Questions about report_recovery_outcome
Report whether a recovery action succeeded, partially succeeded, or failed. Free. It is categorised as a Write tool in the Witness Protocol MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
report_recovery_outcome accepts 8 parameters: notes, outcome, session_id, action_taken, errors_delta, cost_saved_usd, time_saved_min, latency_ms_p95_delta. The full parameter table on this page comes from the server's own tool schema.
Register the Witness Protocol MCP server in PolicyLayer and add a rule for report_recovery_outcome: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Witness Protocol. Nothing to install.
report_recovery_outcome is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the report_recovery_outcome rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for report_recovery_outcome. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
report_recovery_outcome is provided by the Witness Protocol MCP server (delx/witness-protocol). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Witness Protocol, and thousands of servers like it.
This server
Across the catalogue