Paleobiology MCP Server

@cyanheads/paleobiology-mcp-server Search fossil occurrences, resolve taxon fossil ranges, plot diversity through deep time, and look up the geologic time scale via MCP. STDIO or Streamable HTTP. Its 8 documented tools cover paleobiology, dataframe.

People who work with paleobiology and dataframe and want it reachable from Claude, Cursor, VS Code, or another MCP client. The project is written in TypeScript.

VERIFIED ACTIVE

LAST COMMIT 2026-08-25 · ★ 2 · #389 OF 945 MAINTAINED OTHER · VERIFIED 2026-09-18

Apache-2.0 · TypeScript servers · how we verify → /methodology

01 · Install Paleobiology MCP Server

before you install - you'll need

Set MCP_TRANSPORT_TYPE, MCP_LOG_LEVEL before connecting.

Claude Code

claude mcp add cyanheads-paleobiology-mcp-server --transport http https://paleobiology.caseyjhand.com/mcp

Claude Desktop / Cursor / VS Code - add to config

{
  "mcpServers": {
    "cyanheads-paleobiology-mcp-server": {
      "url": "https://paleobiology.caseyjhand.com/mcp"
    }
  }
}

Same JSON for Cursor. For VS Code, rename the top-level key from `mcpServers` to `servers`.

Using another client? Same JSON, different key

Claude Desktop · mcpServers

Cursor · mcpServers

VS Code · servers

Windsurf · mcpServers

Zed · context_servers

Cline · mcpServers

Roo Code · mcpServers

Continue · mcpServers

LibreChat · mcpServers

Gemini CLI · mcpServers

Codex CLI · mcp_servers

Full setup guides: every client.

02 · Evidence

https://paleobiology.caseyjhand.com/mcp

transport: streamable-http

endpoint alive - responded to MCP initialize · probed 2026-09-17

Security posture

What to check before giving this server access to your agent - from the registry, GitHub, and our own probes. We don't score safety; we show what's verifiable.

runs as local process (stdio) - runs on your machine with your user's permissions · remote - your agent's requests go to paleobiology.caseyjhand.com

endpoint auth accepted our unauthenticated MCP initialize - no credentials needed to connect

license Apache-2.0 - declared in the repository

npm package @cyanheads/paleobiology-mcp-server - published under the repo owner's npm scope (@cyanheads)

registry namespace io.github.cyanheads is GitHub-verified and matches the repo owner

03 · What Paleobiology MCP Server can do

Prose above is summarized from the project's README and registry record - no invented capabilities.

What you can build

With this server connected, an agent can run a read-only SQL SELECT over occurrence sets staged on a DataCanvas by paleobiology_search_occurrences. SELECT only, and list the tables and columns staged on a DataCanvas. Call before paleobiology_dataframe_query to discover table and column names.

The 8 tools it gives your agent

Extracted from the project's README - what paleobiology-mcp-server lets an agent do.

paleobiology_search_occurrences
- Search fossil occurrences by taxon, geologic time, geography, and depositional environment. Every row carries both modern and paleo coordinates. The flagship; b
paleobiology_get_taxon
- Resolve a taxon by name or taxon_no to its accepted name, rank, classification, parent, occurrence count, and first/last-appearance (FAD/LAD) range. Run first t
paleobiology_get_diversity
- Compute a diversity / origination / extinction curve for a clade across geologic time, binned by period, epoch, or age. Returns the full bin set inline.
paleobiology_list_intervals
- Look up the geologic time scale - eons through ages with absolute-age (Ma) boundaries and nesting. Translates named intervals ↔ Ma. Served offline from a bundle
paleobiology_search_collections
- Find fossil collections (localities) by area and geologic time, with their formation, lithology, depositional environment, and co-occurring-fossils count. Paged
paleobiology_dataframe_query
- Run a read-only SQL SELECT over occurrence sets staged on a DataCanvas by paleobiology_search_occurrences. SELECT only.
paleobiology_dataframe_describe
- List the tables and columns staged on a DataCanvas. Call before paleobiology_dataframe_query to discover table and column names.
paleobiology_dataframe_drop
- Drop a single staged table to free memory before its TTL expires. Opt-in - registered only when PALEOBIOLOGY_DATAFRAME_DROP_ENABLED=true.

Latest releases

v0.3.5 · 2026-08-25

mcp-ts-core ^0.12.3 and MCP SDK v2 · MCP SDK v2 via @cyanheads/mcp-ts-core ^0.12.3 - HTTP endpoints serve protocol revision 2026-07-28 alongside the 2025 era, and advertised schemas are JSON Schema 2020-12 · Tool…

v0.3.4 · 2026-07-30

PBDB interval fallback · paleobiology_list_intervals falls back to a live PBDB lookup for sub-stage and regional interval names (e.g. Late Maastrichtian, Lancian) the bundled ICS snapshot does not carry, labeled with a…

v0.3.3 · 2026-07-30

offset paging, base_id clade filter, and paged taxon children · paleobiology_search_occurrences gains offset paging with exact next-page notices against PBDB's true match count (#14) · base_id accepted as a clade…

04 · Who maintains Paleobiology MCP Server

paleobiology-mcp-server is maintained by cyanheads. We track 125 MCP servers from cyanheads - 119 actively maintained, 1,816 combined GitHub stars, oldest repo from Dec 2024. Full record: all servers from cyanheads.

  1. obsidian-mcp-server Read, write, search, and surgically edit Obsidian notes, tags, and frontmatter via MCP. ★ 681
  2. mcp-ts-core Agent-native TypeScript framework for MCP servers. ★ 151
  3. pubmed-mcp-server Search PubMed/Europe PMC, fetch articles and full text (PMC/EPMC/Unpaywall), citations, MeSH terms. ★ 148
  4. git-mcp-server Comprehensive Git MCP server enabling native git tools including clone, commit, worktree, & more. ★ 240
  5. clinicaltrialsgov-mcp-server Search ClinicalTrials.gov - find studies, retrieve results, match patients to eligible trials. ★ 94
  6. ntfy-mcp-server Send, manage, and replay ntfy push notifications via MCP. ★ 22

05 · Facts

category
other - ranked #389 of 945 actively-maintained other servers as of 2026-09-18.
release cadence
8 releases in the last 90 days (latest 2026-08-25)
registry
io.github.cyanheads/paleobiology-mcp-server (active, first published 2026-06-28 · 7 versions)
packages
npm:@cyanheads/paleobiology-mcp-server · npm:@cyanheads/paleobiology-mcp-server

06 · Paleobiology MCP Server FAQ

Is Paleobiology MCP Server still maintained?

Yes - as of 2026-09-18, its last commit was 2026-08-25 and it shipped 8 releases in the last 90 days. We re-verify nightly.

What can Paleobiology MCP Server do?

With this server connected, an agent can run a read-only SQL SELECT over occurrence sets staged on a DataCanvas by paleobiology_search_occurrences. SELECT only, and list the tables and columns staged on a DataCanvas. Call before paleobiology_dataframe_query to discover table and column names.

How do I install Paleobiology MCP Server?

Run `npx -y @cyanheads/paleobiology-mcp-server`. The README documents 2 environment variables (MCP_TRANSPORT_TYPE, MCP_LOG_LEVEL) to set first. Set MCP_TRANSPORT_TYPE, MCP_LOG_LEVEL before connecting. You can also paste the ready-made client config above.

Does Paleobiology MCP Server require authentication?

No - the endpoint accepted our unauthenticated MCP initialize when probed on 2026-09-17; you can connect without credentials.

07 · Alternatives to Paleobiology MCP Server