ingest_document

SERVERMeridian SOURCE@meridianmcp/mcp

Medium RISK CLASS

Category Write

Parameters 70 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/ingest-document.md

WHAT IT DOES

What ingest_document does on Meridian

AI agents use ingest_document 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
`tags`	string	—	Comma-separated tags.
`title`	string	—	Note title. Defaults to the file's basename.
`source`	string	—	Provenance URL/path stored on the note. Defaults to file_path.
`content`	string	—	Pre-extracted document text. Use for PDFs and any type Meridian can't parse server-side. Takes precedence over file_path when both are given.
`file_path`	string	—	Path to a .txt/.md/.docx file to extract server-side (stdlib only). For .pdf or other types, pass pre-extracted text as 'content' instead.
`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.

Parameters from the server's own tool schema.

RISK

Why ingest_document is rated Medium

The tool ingests a document and creates a new note/record in the system's persistent memory, which is a reversible write operation. It does not execute code, delete data, or involve financial transactions. The severity is medium because it writes potentially large or sensitive document content into project memory that could be queried by AI agents.

From the tool's definition Turn a Word/PDF/text document into a queryable kind='document' note with a source link — a report, thesis chapter, or spec doc becomes searchable project memory

Risk signalsAccepts file system path (file_path) · Accepts raw HTML/template content (content)

Attacks that exploit this kind of access

RECOMMENDED RULE

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

ingest_document Rate-limited

ingest_document 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": {
    "ingest_document": {
      "limits": [
        {
          "counter": "ingest_document_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 ingest_document call is checked against it from then on.

FAQ

Questions about ingest_document

What does the ingest_document tool do? +

[SUPPORT] Turn a Word/PDF/text document into a queryable kind='document' note with a source link — a report, thesis chapter, or spec doc becomes searchable project memory. Pass file_path OR content (one is required): • file_path → Meridian extracts the text SERVER-SIDE, STDLIB ONLY: .txt/.md/.markdown and source files are read directly; .docx is unzipped and its paragraphs extracted (no python-docx). No new dependencies. • content → use this for .pdf and anything Meridian can't parse server-side: extract the text with YOUR OWN tools first, then pass it here. (Passing file_path for a .pdf returns an error telling you to do this.) title defaults to the file's basename; source defaults to file_path. The stored body is capped (truncated with a '…[truncated]' marker if very long; the kept prefix stays searchable). Meridian never summarizes — pass a summary as content if you want one stored instead of the raw text. Returns the created note (id, slug, title, source). 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 ingest_document accept? +

ingest_document accepts 7 parameters: tags, title, source, content, file_path, project_id, project_name. The full parameter table on this page comes from the server's own tool schema.

How do I enforce a policy on ingest_document? +

Register the Meridian MCP server in PolicyLayer and add a rule for ingest_document: 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 ingest_document? +

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

Can I rate-limit ingest_document? +

Yes. Add a rate_limit block to the ingest_document 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 ingest_document completely? +

Set action: deny in the PolicyLayer policy for ingest_document. 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 ingest_document? +

ingest_document 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

The MCP Attack Database →

Guides

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