get_findings
[MAINTENANCE] Read-only (c35370cc): read stored session_findings for a project (newest first), optionally scoped by key and/or session_id. The read side of store_finding. Persistent-state disclosure: on hosted Meridian, supplied text and project/session metadata are sent to and stored in Meridian...
This record as markdown: /tools/io-github-ajc3xc-meridian/get-findings.md
What get_findings does on Meridian
AI agents call get_findings to retrieve information from Meridian without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
key | string | — | Only findings in this bucket. |
limit | integer | — | Max rows (default 50). |
project_id | string | — | |
session_id | string | — | Only findings from this session. |
project_name | string | — | Project name — an alternative to project_id. |
Parameters from the server's own tool schema.
Why get_findings is rated Low
This tool retrieves and queries stored session findings without modifying, deleting, or executing operations. It is purely a Read operation. However, severity is elevated to 'medium' rather than 'low' because the description explicitly warns of 'Persistent-state disclosure'—the findings may contain sensitive project context, session metadata, and AI reasoning artifacts that could expose proprietary code, design…
From the tool's definition 'Read-only' descriptor; 'read stored session_findings'; 'The read side of store_finding'; retrieves project findings optionally filtered by key and/or session_id.
Attacks that exploit this kind of access
The rule that runs get_findings 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 get_findings, this is the rule to start with:
get_findings is read-only, so it stays allowed. 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 get_findings call is checked against it from then on.
Questions about get_findings
[MAINTENANCE] Read-only (c35370cc): read stored session_findings for a project (newest first), optionally scoped by key and/or session_id. The read side of store_finding. 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 Read tool in the Meridian MCP Server, which means it retrieves data without modifying state.
get_findings accepts 5 parameters: key, limit, project_id, session_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 get_findings: 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.
get_findings is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get_findings 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 get_findings. 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.
get_findings 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.
This server
Across the catalogue