ingest_paper_fulltext

THE RISK

Medium Risk

Why ingest_paper_fulltext needs a policy

This tool fetches a PDF and writes/stores a parsed structured document into the system. It creates new data (the ingested, parsed document) in the research workflow, making it a Write operation. It is reversible in the sense that the ingested document could be removed.

From the tool's definition Resolve and ingest a full-text PDF from DOI/URL/local file, then parse into a structured document

Documented attack patterns abuse exactly the kind of access ingest_paper_fulltext gives an agent:

POLICY

How to control ingest_paper_fulltext

PolicyLayer is an MCP gateway — it sits between your AI agents and ScholarMCP, and nothing reaches the server without passing your rules. This is the rule we recommend for ingest_paper_fulltext:

policy.json

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

ingest_paper_fulltext 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.

Create a free account and register ScholarMCP — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

LIMIT THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More ScholarMCP tools

Read build_reference_list Generate CSL-formatted bibliography and BibTeX entries from manuscript context or explicit Read extract_granular_paper_details Extract claims, methods, limitations, datasets, metrics, and section-aware summaries from Read get_author_info Retrieve a Google Scholar author profile and top publications by author name. Read get_ingestion_status Get the status of a previously started ingest_paper_fulltext job. Read search_google_scholar_advanced Search Google Scholar using keyword, author, year-range, phrase, and exclusion filters. Read search_google_scholar_key_words Search Google Scholar using keywords and return paper metadata. Read search_literature_graph Search multiple scholarly metadata providers (OpenAlex, Crossref, Semantic Scholar, option Read suggest_contextual_citations Recommend citations from the federated literature graph based on manuscript context.

All 10 ScholarMCP tools →

Write tools on other servers

M-Team MCP Server download_torrent YouTube MCP Server generate_video_title Android Forensics ADB MCP Server combine_reports 0xarchive web3_signup

Go deeper

The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Argument validation → Checking tool call arguments against schema and policy before they run.
Scoped token → Per-person credentials that grant a defined subset of servers and tools.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about ingest_paper_fulltext

What does the ingest_paper_fulltext tool do? +

Resolve and ingest a full-text PDF from DOI/URL/local file, then parse into a structured document using GROBID/simple fallback pipeline. It is categorised as a Write tool in the ScholarMCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on ingest_paper_fulltext? +

Register the Scholar MCP server in PolicyLayer and add a rule for ingest_paper_fulltext: 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 ScholarMCP. Nothing to install.

What risk level is ingest_paper_fulltext? +

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

Can I rate-limit ingest_paper_fulltext? +

Yes. Add a rate_limit block to the ingest_paper_fulltext 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_paper_fulltext completely? +

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

ingest_paper_fulltext is provided by the Scholar MCP server (lstudlo/scholarmcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every ScholarMCP tool call.

Start from ScholarMCP, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →