index_figure
[MAINTENANCE] c623e648 — index ONE figure into the SEMANTIC figure index against a document already stored in the doc-structure store — populated by ingest_document (which registers a docx/latex document's structure here in addition to storing the flat note text). Pass the SAME source/path you in...
This record as markdown: /tools/io-github-ajc3xc-meridian/index-figure.md
What index_figure does on Meridian
AI agents use index_figure 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 |
|---|---|---|---|
doc | string | Yes | The stored document's source (the path/URL you ingested it under via ingest_document, which registers a docx/latex document in the doc-structure store). |
caption | string | — | The figure's caption (drives normalized-caption dedup/similarity). |
file_path | string | — | Path to the figure's asset on disk (checked for existence; missing is flagged, not fatal). |
project_id | string | — | |
project_name | string | — | Project name — an alternative to project_id; resolved to the id internally. project_id wins if both are given. |
semantic_label | string | — | Optional human label for the figure (e.g. 'apparatus diagram'). |
Parameters from the server's own tool schema.
Why index_figure is rated Medium
This tool writes a figure entry into a semantic index store. It creates/modifies index data (caption deduplication, similarity entries) but does not execute code, delete data, or involve financial operations. It is reversible in principle (index entries can be removed), making Write the appropriate category. Severity is low since it only affects an internal search/semantic index with limited blast radius.
From the tool's definition index ONE figure into the SEMANTIC figure index...adds caption dedup + similarity, it does not replace placement
Risk signalsAccepts file system path (file_path) · Bulk/mass operation — affects multiple targets
Attacks that exploit this kind of access
The rule that runs index_figure 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 index_figure, this is the rule to start with:
index_figure 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 Meridian, apply this rule, and every index_figure call is checked against it from then on.
Questions about index_figure
[MAINTENANCE] c623e648 — index ONE figure into the SEMANTIC figure index against a document already stored in the doc-structure store — populated by ingest_document (which registers a docx/latex document's structure here in addition to storing the flat note text). Pass the SAME source/path you ingested under as doc. This is the figure parallel of index_equation and is COMPLEMENTARY to the structural kind='figure' section-tree placement (it adds caption dedup + similarity, it does not replace placement). Provide file_path and/or caption. Before inserting, the normalized caption is fuzzy-matched against every figure already indexed for this document — a near-duplicate is NOT silently dropped (the figure is still inserted) but IS surfaced via near_duplicates:[{figure_id, matched_id, matched_caption, score}] so you can spot an accidental re-index. The referenced file_path is checked on disk: a missing file is FLAGGED (file_exists on the row + a missing_files entry), never a hard failure. Returns {figure, near_duplicates, missing_files}. 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.
index_figure accepts 6 parameters: doc, caption, file_path, project_id, project_name, semantic_label. Required: doc. 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 index_figure: 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.
index_figure 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 index_figure 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 index_figure. 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.
index_figure 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