find_outputs_by_source
[SUPPORT] 2ae25966 — READ-ONLY reverse provenance lookup over a run's OUTPUTS tree: the mirror image of resolve_figure_output's forward direction (figure -> source). Given a script or data file's source_path, scans the same local DuckDB outputs index search_outputs/annotate_outputs use for every ...
This record as markdown: /tools/io-github-ajc3xc-meridian/find-outputs-by-source.md
What find_outputs_by_source does on Meridian
AI agents call find_outputs_by_source 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 |
|---|---|---|---|
limit | integer | — | Max matched outputs to return, newest-first by mtime (default 25). |
outputs_dir | string | Yes | Absolute path to the outputs directory tree to index and search (same value you pass to search_outputs). |
source_path | string | Yes | The generating script or data file to trace forward from (e.g. 'analysis/run.py') — matched against each indexed output's recorded generating_script. |
Parameters from the server's own tool schema.
Why find_outputs_by_source is rated Low
find_outputs_by_source retrieves and queries provenance metadata from a local DuckDB index to find outputs that match a given source path. It has no side effects, creates no data, executes no external code, and modifies nothing. The 'READ-ONLY' designation and search/scan semantics clearly place this in the Read category with low severity.
From the tool's definition Tool description explicitly states 'READ-ONLY reverse provenance lookup' and 'scans...for every indexed output' — performs querying/searching over existing data without modification.
Risk signalsAccepts file system path (source_path) · Bulk/mass operation — affects multiple targets
Attacks that exploit this kind of access
The rule that runs find_outputs_by_source 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 find_outputs_by_source, this is the rule to start with:
find_outputs_by_source 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 find_outputs_by_source call is checked against it from then on.
Questions about find_outputs_by_source
[SUPPORT] 2ae25966 — READ-ONLY reverse provenance lookup over a run's OUTPUTS tree: the mirror image of resolve_figure_output's forward direction (figure -> source). Given a script or data file's source_path, scans the same local DuckDB outputs index search_outputs/annotate_outputs use for every indexed output whose recorded generating_script traces back to it — an exact (case/slash-insensitive) string match OR a basename match, so 'analysis/run.py' also matches an output recorded with generating_script='run.py'. This is the direction plain exact-path resolution can never answer, because that always starts from the output side: 'what did this script/data file produce?' — useful for auditing a stale Outputs_*_BACKUP folder mess by walking a source file's outputs forward, newest first, and comparing against what a document actually cites. Returns {outputs_dir, source_path, outputs:[{path, generating_script, is_archival, canonical_path, sha256, kind, size, mtime, csv_columns, json_keys}], total} sorted newest-first by mtime; total is the full match count before limit truncation. outputs is empty (not an error) when nothing in the tree cites this source, or when outputs_dir doesn't exist. It is categorised as a Read tool in the Meridian MCP Server, which means it retrieves data without modifying state.
find_outputs_by_source accepts 3 parameters: limit, outputs_dir, source_path. Required: outputs_dir, source_path. 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 find_outputs_by_source: 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.
find_outputs_by_source 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 find_outputs_by_source 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 find_outputs_by_source. 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.
find_outputs_by_source 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