# Pith MCP server

Source: https://glimind.com/server/mcp-registry%2Fscience.pith%2Fpith
Registry id: `mcp-registry/science.pith/pith`
Status: live (checked 2026-10-27T10:59:11.110Z)

## Verdict

Pith MCP server answered 100% of Glimind's liveness checks over 30 days, better than 42% of MCP servers, with 377 ms median handshake and 0 outages in 90 days. Its agent-readiness grade is A (96/100) across 24 tools, costing an agent about 4,528 tokens to load. Checked every few minutes; no tool is ever called.

## Measurements (30 days)

| Metric | Value | Better than |
|---|---|---|
| Uptime, 30 days | 100% | 42% of MCP servers |
| Median handshake latency | 377 ms | 55% of MCP servers |
| p95 handshake latency | 2973 ms | — |
| Checks in 30 days | 4,643 | — |
| Outages, 90 days | 0 | — |
| Median recovery | — | — |
| Agent-readiness score | 96/100 (A) | 82% of MCP servers |
| Tools | 24 | — |
| Tool-list size for an agent | ~4,528 tokens | 40% of MCP servers |
| Days observed | 29 | — |

## Install

```json
{
  "mcpServers": {
    "pith-mcp-server": {
      "type": "http",
      "url": "https://pith.science/mcp"
    }
  }
}
```

Claude Code:

```sh
claude mcp add --transport http pith-mcp-server https://pith.science/mcp
```

## Tools (24)

- `analyze_paper_claims`: The structured argument of one specific paper: what it actually asserts, the premises it assumes, the machinery connecting those premises to the claim, and the 
- `ask_field`: Read the papers closest to a question and return, for each, whether its own abstract sentences answer yes, no or not addressed, with the deciding sentence quote
- `check_claim`: Which arXiv papers support a scientific statement, which contradict it, and which study it without deciding, each with the paper's own main claim quoted and the
- `check_my_draft`: Resolve each reference in a draft, flag retracted works, and for arXiv papers show how later papers cite them: as support, and whether any contest them, with th
- `citation_neighbors`: One hop from a paper: every reference entry with its resolved work identity, the papers that cite it, and, where a record exists, the citing sentences with thei
- `find_passages`: Author sentences the classifier labeled with one role, across every stored record, each with its probability and paper. Abstract-tier records cover limitation, 
- `get_claims`: Alias of analyze_paper_claims: the same ledger of what the paper asserts, its premises, machinery, and falsifier, in argument order.
- `get_falsifier`: Alias of get_paper_falsifier: the same falsifier and watcher count.
- `get_paper_falsifier`: The falsifier for one specific paper's core claim: the concrete observation, experiment, or computation that would settle or disprove it, plus how many people a
- `get_record`: The compiled record of one paper: the authors' own sentences, arranged with typed labels. It carries the main claim in the authors' words, each abstract sentenc
- `get_review`: Pith's review of one specific paper, in one call: the verdict, confidence, novelty and correctness scores, one-line summary, weakest assumption, and the paper's
- `get_reviewer_record`: A reviewer's published signed reviews and, when present, their calibration record (Brier score, open predictions, positivity skew). Call this when the user asks
- `get_signed_reviews`: Published human signed reviews of one paper: reviewer identity, axis deltas against the machine review, claim verdicts, defects, predictions, and who paid. Call
- `latest_reviews`: The papers Pith reviewed most recently, newest first. Call this when the user asks what is new, notable, or recently reviewed in a field or overall. days caps h
- `my_citations`: For the papers claimed on the account behind your key: how many papers cite each, whether they cite it as support, extension or disagreement, and the citing sen
- `my_reviews`: Pith's machine review verdict and the count of published signed human reviews for each paper claimed on the account behind your key. Needs a personal key.
- `paper_bridge`: Whether either paper cites the other, the resolved works both cite (on or off arXiv), and the papers that cite both.
- `paper_connections`: What other arXiv papers do with this paper, and what it does with the arXiv papers it cites: builds on, uses the method or tool, uses the data, compares with, c
- `paper_packet`: One paper's compiled record, small enough to hold beside others: the main claim and contribution in the authors' words, each abstract sentence with its role and
- `record_coverage`: Sources read and levels run for one paper's record, or the number of stored records by tier. Call before treating an empty result as a finding: an empty list me
- `resolve_paper`: Turn a pasted arXiv id, arXiv URL, DOI, or Pith Number into the arXiv id the other tools key on. ``resolved`` is false when the input did not become an arXiv id
- `search_claims`: Full-text search over every scientific claim Pith has extracted, across all reviewed papers. Call this when the user asks who claims something, whether a claim 
- `search_papers`: Search Pith-reviewed papers by title and abstract. Call this when the user names a research topic, phenomenon, method, or paper title without an identifier, or 
- `verify_citation`: Whether the cited paper's own sentences support what a sentence attributes to it: supports, partly supports (a condition is missing), contradicts, or not addres

Measured by Glimind (https://glimind.com): MCP handshake + tool list only, no tool is ever called. CC BY 4.0.