AI & Machine Learning

aiconfpaper.com

Provides semantic search and detailed metadata access for AI conference papers, including abstracts, BibTeX, citation counts, and code links.

1 endpoint5 known toolsFirst detected August 24, 2026Last detected August 24, 2026

ENDPOINT 1

https://aiconfpaper.com/mcp

No auth detected

MCP server metadata

Name: aiconfpaper
Version: 1.0.0

Capabilities

tools

Server instructions

Semantic search over millions of accepted AI-conference papers (NeurIPS, ICML, ICLR, CVPR, ECCV, ICCV, ACL, EMNLP, CoRL, ICRA, IROS, RSS, AAAI, IJCAI, ICASSP and more; 2015-2026). Start with search_papers — the query is free text (keywords, a sentence, or a whole abstract), ranked by embedding similarity. Then batch_get_papers for full records (abstract, BibTeX, links.arxiv_src LaTeX source bundle, links.code); find_similar_papers expands from a seed paper; list_facets gives valid venue filter values. links.arxiv_src and links.code can be null (retry a detail call once for arxiv_src; verify a code repo against the paper title before trusting it). Tool calls need a free API key sent as 'Authorization: Bearer acp_...' — create one at https://aiconfpaper.com/account. Collections (create/add/export) are on the REST API: https://aiconfpaper.com/developers.

Known tools 5

search_papers

Semantic search over accepted papers from top AI conferences.

Inferred read-only

get_paper

Full record for one paper_id from search results: abstract, BibTeX, live citation count, and links including arxiv_src (the LaTeX source bundle, https://arxiv.org/src/{id}) and code.

Inferred read-only

batch_get_papers

Batch version of get_paper: full abstracts + BibTeX + links for up to 50 paper_ids in ONE call — use this instead of looping get_paper.

Inferred read-only

find_similar_papers

Nearest neighbors of a seed paper in embedding space (instant — reuses its stored vector).

Inferred read-only

list_facets

Valid `venues` filter values with per-venue year coverage ({venue: {min, max, count}}), tier values, and the overall year range — call once to construct valid search filters instead of guessing venue spellings.

Inferred read-only

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.aiconfpaper]
url = "https://aiconfpaper.com/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "aiconfpaper": {
      "type": "http",
      "url": "https://aiconfpaper.com/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: aiconfpaper
Remote MCP URL: https://aiconfpaper.com/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "aiconfpaper": {
      "url": "https://aiconfpaper.com/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "aiconfpaper": {
      "type": "http",
      "url": "https://aiconfpaper.com/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "aiconfpaper",
  "transport": "streamable-http",
  "url": "https://aiconfpaper.com/mcp"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

TRUST AND VERIFICATION EVIDENCE

Loading Trust v2 evidence…

Checking the associated registrable domain. The BuiltWith key remains server-side.

Indexed

Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.