phylokit-mcp server
Phylogenetic inference via IQ-TREE 3 — never returns a topology without its support
not scanned yet
0 stars185 downloads/wk
Reviews
Write oneNobody has reviewed phylokit-mcp yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
phylokit-mcp tools
No tool declarations could be read from the package source. They show once the server is installed.
How phylokit-mcp compares
Against every graded MCP server, from our own scans and uptime checks. Updated after each scan run.
- Safety score
- 92/100
- higher than 95% of 48,255 servers
- Downloads a week
- 185
- more than 74% of 12,191 servers with a package
Release history: 6 versions in the registry since 2026-08-02, latest 2026-10-26, typically one every 7 days.
Install phylokit-mcp in Claude Code, Cursor or VS Code
claude mcp add phylokit-mcp -- uvx phylokit-mcp
What the publisher says
From the phylokit-mcp repository's README, as published. We do not edit it. Read it on GitHub
phylokit-mcp
<!-- mcp-name: io.github.musharna/phylokit-mcp -->
Phylogenetic inference over MCP, driving IQ-TREE 2 through piqtree.
A topology without support is not a result. infer_tree always runs a bootstrap and always returns per-clade support. There is no flag to skip it.
6 tools, 105 tests against real IQ-TREE and real MAFFT (no mocked engine), 23 mutation checks, and a real-process JSON-RPC handshake test.
Why the rule
A maximum-likelihood tree looks identical whether or not the data support it. Measured here, on alignments simulated from a known 7-taxon tree so the right answer is not in doubt:
At 60 sites the tree contains a clade (C,D,G) that does not exist and omits one that does (E,F,G). Both runs return a fully resolved Newick string of the same shape; nothing about the topology itself distinguishes them. The support values do — and the false clade is the lowest-supported one in the tree.
That is the entire argument for this server. Returning a bare tree returns a result the caller cannot evaluate.
What it reports that a Newick string cannot
from the reported tree. A support-annotated Newick string has nowhere to attach these, so the standard format silently drops them.
- Conflicting clades — groupings the data support at ≥0.70 that are absent
number, before any individual grouping is repeated as fact.
- fractionresolved** — the share of clades clearing 0.70. The headline
above, simulated under JC, the AIC winner is F81, with several models inside the conventional ±2 indistinguishability margin. A winner without its margin is a claim the numbers do not support.
- Model runners-up with ΔAIC — not just a winner. On the 300-site alignment
A 10,000-site alignment of near-identical sequences supports nothing.
- Length versus evidence — nparsimonyinformative alongside n_sites.
Tools
Install
pip install phylokit-mcpShortened. The full README is on GitHub.
Nothing above is checked by us. What we check is on the safety report.
phylokit-mcp: common questions
- Is phylokit-mcp server safe?
- Yes, by our scan: it is graded A (92/100). Read the phylokit-mcp safety report
- How do I install phylokit-mcp?
- It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
- Does phylokit-mcp need an API key?
- No secret keys are declared. It reads 2 settings from the environment.
- Is phylokit-mcp maintained?
- The last commit was 34 days ago (2026-10-01). The latest release is v0.8.0.
- How does phylokit-mcp compare with other MCP servers?
- safety score 92/100 (higher than 95% of 48,255 servers); downloads a week 185 (more than 74% of 12,191 servers with a package). Full comparison.