Search 200M+ academic papers on Semantic Scholar by keyword. Returns titles, authors, year, venue, citation counts, DOI, and open-access PDF links. Optionally filter by year range and field of study. Keyless.
AI agents call search_papers to retrieve information from Mcp Semanticscholar without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
year | string | — | Filter by publication year or range, e.g. "2023" or "2020-2024". |
limit | number | — | Max results to return (default 10, max 25). |
query | string | Yes | Search query, e.g. "transformer attention mechanism" or "CRISPR gene editing". |
fields_of_study | string | — | Filter by field of study, e.g. "Computer Science", "Medicine", "Biology", "Physics". |
Parameters from the server's own tool schema.
search_papers is a query tool that retrieves existing academic paper metadata from the Semantic Scholar database. It reads and returns information without modifying, executing operations, or causing irreversible changes. The optional filtering parameters (year range, field of study) are read-time constraints, not write operations.
From the tool's definition Tool description states it 'Search[es]' and 'Returns' data (titles, authors, year, venue, citation counts, DOI, open-access links). No creation, modification, deletion, code execution, or financial operations are mentioned.
Risk signalsAccepts freeform code/query input (query)
Attacks that exploit this kind of access
Search 200M+ academic papers on Semantic Scholar by keyword. Returns titles, authors, year, venue, citation counts, DOI, and open-access PDF links. Optionally filter by year range and field of study. Keyless. It is categorised as a Read tool in the Mcp Semanticscholar MCP Server, which means it retrieves data without modifying state.
search_papers accepts 4 parameters: year, limit, query, fields_of_study. Required: query. The full parameter table on this page comes from the server's own tool schema.
Register the Mcp Semanticscholar MCP server in PolicyLayer and add a rule for search_papers: 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 Mcp Semanticscholar. Nothing to install.
search_papers 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 search_papers 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 search_papers. 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.
search_papers is provided by the Mcp Semanticscholar MCP server (https://gateway.pipeworx.io/semanticscholar/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →