MCP server wrapping the Semantic Scholar Academic Graph API — paper lookup, citation tracing, recommendations, author info
Semantic MCP server exists for a simple reason — assistants are far more useful when they can act on Semantic directly instead of describing what you should do. MCP server wrapping the Semantic Scholar Academic Graph API — paper lookup, citation tracing, recommendations, author info.
Designed for AI assistants like Claude to help with literature review, citation analysis, and research discovery. Works with any MCP-compatible client (Claude Desktop, Claude Code, or custom integrations).
The server ships on npm as @yogsoth-ai/semantic-scholar-mcp, so your MCP client can launch it on demand — there is no separate build step. Add the server block to your client's configuration, restart it, and the tools register themselves.
Once Semantic is connected, these are the calls the assistant has available:
paper — Get full metadata for a single paper (supports ARXIV, DOI, S2 ID, PMID, URL formats)paperBatch — Batch fetch up to 500 papers in one callreferences — Get papers cited by a paper (outgoing citations with context and intent)citations — Get papers citing a paper (incoming citations with context and intent)recommendations — Get paper recommendations based on positive/negative seed papersrelevanceSearch — Search papers by keyword with filters (year, field, citations, open access)author — Get author profile (name, affiliations, h-index, paper/citation counts)authorPapers — Get all papers by an author with full metadata and paginationYou will need one environment variable: SS_API_KEY. The server will not start without them, which is usually why the tools fail to appear on a first run. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.
This sits in the developer tooling group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. Semantic's toolset — paper, paperBatch, references and 5 more — is a fair guide to whether it matches your workflow. It is maintained by pthahnix; worth a glance at recent repository activity before you build anything load-bearing on it.
This entry was verified against Semantic's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.
| Tool | What it does |
|---|---|
| paper | Get full metadata for a single paper (supports ARXIV, DOI, S2 ID, PMID, URL formats) |
| paperBatch | Batch fetch up to 500 papers in one call |
| references | Get papers cited by a paper (outgoing citations with context and intent) |
| citations | Get papers citing a paper (incoming citations with context and intent) |
| recommendations | Get paper recommendations based on positive/negative seed papers |
| relevanceSearch | Search papers by keyword with filters (year, field, citations, open access) |
| author | Get author profile (name, affiliations, h-index, paper/citation counts) |
| authorPapers | Get all papers by an author with full metadata and pagination |
{
"mcpServers": {
"semantic-scholar-1": {
"command": "npx",
"args": ["-y", "@yogsoth-ai/semantic-scholar-mcp"],
"env": {
"SS_API_KEY": "your-value"
}
}
}
}Add to claude_desktop_config.json, then restart Claude Desktop.
| Variable | Description | Required |
|---|---|---|
| SS_API_KEY | Credential the server authenticates with. | Yes |
Kill hallucinated APIs — version-accurate, up-to-date library documentation injected straight into context.
Microsoft's official browser automation server — drive a real browser through the accessibility tree, no screenshots needed.
GitHub's official server — repos, issues, pull requests, Actions and code security, straight from your assistant.
Issue tracking at the speed of conversation — Linear's official hosted server with OAuth and zero install.
Local repository surgery — status, diffs, commits, branches and history for any repo on disk.
Timezone sanity for AI — current time anywhere and correct conversions, without the model doing date math.