paper_get_text
Return the full text of an indexed open-access paper by its corpus key (e.g. 'arxiv:2310.12345'), paginated by passage. Use from_seq + max_passages to page through it. For works not indexed locally, returns a pointer to find the open-access URL via paper_search / paper_details.
This record as markdown: /tools/io-github-blackboxfoundry-livedatalink/paper-get-text.md
What paper_get_text does on Livedatalink
AI agents call paper_get_text to retrieve information from Livedatalink 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 |
|---|---|---|---|
from_seq | number | — | Passage index to start from (0-based, default 0). |
paper_key | string | Yes | Corpus key of an indexed paper, e.g. 'arxiv:2310.12345' or 'pmc:PMC1234567'. |
max_passages | number | — | Maximum passages to return per call (default 40, max 200). |
Parameters from the server's own tool schema.
Why paper_get_text is rated Low
This is a straightforward data retrieval tool that fetches and returns content from an indexed academic paper database. It performs no write operations, destructive actions, or code execution. The pagination mechanism and pointer-returning for non-indexed works are standard read-only information retrieval patterns. Low severity because misuse would only expose publicly available open-access academic content.
From the tool's definition Tool returns full text of indexed papers by corpus key with pagination parameters (from_seq, max_passages). The description uses retrieval language: 'Return the full text', 'paginated', 'returns a pointer'.
Attacks that exploit this kind of access
The rule that runs paper_get_text safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Livedatalink, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For paper_get_text, this is the rule to start with:
paper_get_text 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 Livedatalink, apply this rule, and every paper_get_text call is checked against it from then on.
Questions about paper_get_text
Return the full text of an indexed open-access paper by its corpus key (e.g. 'arxiv:2310.12345'), paginated by passage. Use from_seq + max_passages to page through it. For works not indexed locally, returns a pointer to find the open-access URL via paper_search / paper_details. It is categorised as a Read tool in the Livedatalink MCP Server, which means it retrieves data without modifying state.
paper_get_text accepts 3 parameters: from_seq, paper_key, max_passages. Required: paper_key. The full parameter table on this page comes from the server's own tool schema.
Register the Livedatalink MCP server in PolicyLayer and add a rule for paper_get_text: 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 Livedatalink. Nothing to install.
paper_get_text 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 paper_get_text 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 paper_get_text. 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.
paper_get_text is provided by the Livedatalink MCP server (https://livedatalink.ai/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Livedatalink, and thousands of servers like it.
This server
Across the catalogue