save_finding

SERVERMeridian SOURCE@meridianmcp/mcp

Medium RISK CLASS

Category Write

Parameters 61 required

Recommended Rate-limitedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/io-github-ajc3xc-meridian/save-finding.md

WHAT IT DOES

What save_finding does on Meridian

AI agents use save_finding to create or update resources in Meridian, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Meridian environment.

Parameter	Type	Required	Description
`summary`	string	Yes	The finding text (markdown). Its first line becomes the note title.
`project_id`	string	—
`source_url`	string	—	Provenance URL/path stored on the note.
`decision_id`	string	—	Optional pinned-decision id to link this finding to (tagged decision:<id>).
`source_type`	string	—	Where the finding came from. Default web; unknown values fall back to web.
`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.

RISK

Why save_finding is rated Medium

This tool creates new persistent notes by capturing findings, which is a write/create operation with reversible side effects (notes can presumably be edited or deleted). The tool generates durable, addressable artifacts in persistent state. While it does not modify existing data or destroy anything, and does not execute arbitrary code or move money, its primary function is to create and store structured data.

From the tool's definition 'turn a finding into a durable, addressable note' + 'summary's first line becomes the note title; the note is tagged' + 'Returns the note' — creates and stores new note records persistently in Meridian service

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs save_finding 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 save_finding, this is the rule to start with:

save_finding Rate-limited

save_finding 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.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "save_finding": {
      "limits": [
        {
          "counter": "save_finding_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect Meridian, apply this rule, and every save_finding call is checked against it from then on.

FAQ

Questions about save_finding

What does the save_finding tool do? +

[SUPPORT] Phase-agnostic capture primitive: turn a finding into a durable, addressable note with provenance — works with ANY source (Claude's built-in web search, the arXiv MCP, Serena, a teammate). Decoupled from search so capture survives regardless of how you found it. The summary's first line becomes the note title; the note is tagged 'finding' + the source_type. Optionally links to a pinned decision. Returns the note. 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 Write tool in the Meridian MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

What parameters does save_finding accept? +

save_finding accepts 6 parameters: summary, project_id, source_url, decision_id, source_type, project_name. Required: summary. The full parameter table on this page comes from the server's own tool schema.

How do I enforce a policy on save_finding? +

Register the Meridian MCP server in PolicyLayer and add a rule for save_finding: 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.

What risk level is save_finding? +

save_finding is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit save_finding? +

Yes. Add a rate_limit block to the save_finding 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.

How do I block save_finding completely? +

Set action: deny in the PolicyLayer policy for save_finding. 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.

What MCP server provides save_finding? +

save_finding 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.

KEEP EXPLORING

More on Meridian, and thousands of servers like it.

This server

All 175 Meridian tools →

Across the catalogue

save_snapshot on Why Did You Render →save_tags on Mcptube Vision → The MCP Attack Database →

Guides

Govern customer-ops agents →Argument validation →Scoped token →