run_verification
[SUPPORT] 0e973e52 — run the project's stored test_cmd on YOUR local machine via the tunnel and return a REAL, structured result — not self-reported. Fields: {exit_code, passed, failed, stdout_tail, stderr_tail, status, timed_out}. Returns {status: 'not_configured'} (never an error) when no test_...
This record as markdown: /tools/io-github-ajc3xc-meridian/run-verification.md
What run_verification does on Meridian
AI agents invoke run_verification to trigger actions in Meridian. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call: builds kicked off, notifications sent, workflows started.
| Parameter | Type | Required | Description |
|---|---|---|---|
project_id | string | — | Meridian project id — whose stored test_cmd to run. |
project_name | string | — | Project name — an alternative to project_id; resolved to the id internally. project_id wins if both are given. |
Parameters from the server's own tool schema.
Why run_verification is rated High
This tool executes external commands/scripts on the user's local machine with results that depend entirely on what test_cmd is configured. While nominally for running tests, the architecture allows arbitrary command execution.
From the tool's definition The tool description explicitly states it will 'run the project's stored test_cmd on YOUR local machine via the tunnel' and returns structured execution results including exit_code, stdout_tail, stderr_tail, and status.
Attacks that exploit this kind of access
The rule that runs run_verification safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Meridian, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For run_verification, this is the rule to start with:
run_verification stays usable, but rate-capped: a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Meridian, apply this rule, and every run_verification call is checked against it from then on.
Questions about run_verification
[SUPPORT] 0e973e52 — run the project's stored test_cmd on YOUR local machine via the tunnel and return a REAL, structured result — not self-reported. Fields: {exit_code, passed, failed, stdout_tail, stderr_tail, status, timed_out}. Returns {status: 'not_configured'} (never an error) when no test_cmd is set; call set_executor_config(test_cmd='pixi run test') first. Requires an active meridian --tunnel; the hosted server has no access to your machine (same architectural class as ingest_document / search_code_semantic / search_outputs — decision 0dedff91). Per-project: only runs when test_cmd is configured for that project. Persistent-state disclosure: on hosted Meridian, supplied text and project/session metadata are sent to and stored in Meridian's service; self-hosted deployments keep them in the configured local SQLite/Postgres database. This data is visible in the dashboard/API and later project context or handoffs. Delete individual tasks, notes, or decisions where supported, or delete the project/account using the documented controls. Do not include secrets. It is categorised as a Execute tool in the Meridian MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
run_verification accepts 2 parameters: project_id, project_name. The full parameter table on this page comes from the server's own tool schema.
Register the Meridian MCP server in PolicyLayer and add a rule for run_verification: 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 Meridian. Nothing to install.
run_verification is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the run_verification 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 run_verification. 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.
run_verification is provided by the Meridian MCP server (@meridianmcp/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Meridian, and thousands of servers like it.
Across the catalogue