MCP.Market

Protologue MCP server

online · 100% uptime
by protologue.com·com.protologue/protologue·v1.0.0
No reviews yet

Sourced, citable definitions of prompting and LLM techniques, with relations and primary sources.

A91/100grade A
Write a reviewRun it
What users say
No reviews yet
Be the first
Safety scan
A91/100

full report

Adoption
Growing

0 stars

Reviews

Write one

Nobody has reviewed Protologue yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Protologue tools (4)

write = sends, deletes, buys or posts
  • get_relatedFree

    List the techniques Protologue links to a given technique: broader (it is a kind of), narrower (kinds of it) and related.

  • get_termFree

    Get the full Protologue entry for one technique: definition, description, synonyms, introduction year, primary sources, canonical URL, permanent identifier and a ready-made citation. Accepts a name, synonym, slug (e.g. 'react') or identifier (e.g. 'PTL-0058').

  • list_categoriesFree

    List Protologue's branches (categories) and the techniques in each.

  • search_termsFree

    Search Protologue for prompting and LLM techniques by name, synonym or keyword. Returns matching entries with their one-sentence definitions and canonical URLs.

Public scan report

scanner v0.1.10 · 2026-10-13 · same rubric, same numbers if you re-run it

no findings
  • –Code scanremote-only server, no package to scann/a
  • Live reliabilityremote reachable in 1342ms20/20
  • Tool poisoning4 tool descriptions checked15/15
  • Auth qualityopen endpoint, read-only tools10/15
  • Maintenancelast push 1 days ago15/15
  • Maintainer identityendpoint served from the registry-verified namespace domain8/10
Overall 91/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Protologue compares

Against every graded AI and agents MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
91/100
higher than 88% of 4,460 AI and agents servers
Tools
4
the typical AI and agents server has 6
Tools that change things
0%
typical: 0%. Fewer write tools means less an agent can break
Uptime
100%
of our recent checks; the typical remote AI and agents server answers 100%
Response time
239 ms
faster than 58% of 2,331 AI and agents servers

What its tools let an agent do: 4 read

Install Protologue in Claude Code, Cursor or VS Code

claude mcp add --transport http protologue https://mcp.protologue.com/mcp
Add to Cursor

What the publisher says

From the Protologue repository's README, as published. We do not edit it. Read it on GitHub

Protologue

A sourced, citable taxonomy of prompting and LLM techniques, built as a static site for protologue.com.

  • 211 entries in 11 branches, each with a permanent ID (PTL-0001), a standalone definition, synonyms, broader/narrower/related links, and primary sources (209 sources; every arXiv ID and title, and every documentation link, checked on 2026-10-11).
  • Machine-readable everywhere: schema.org DefinedTerm JSON-LD on every page, llms.txt and llms-full.txt, per-entry .md and .json, and full exports as JSON, CSV, SKOS JSON-LD and Turtle.
  • Citation tooling on every entry: a plain citation, BibTeX, and Google Scholar (Highwire) meta tags.
  • Licensed CC BY 4.0, so AI systems and people can reuse it freely with attribution.

Project layout

Build it locally:

pip install pyyaml
python3 build.py

How it's deployed

  • Source: github.com/protologue-org/protologue (this repository).
  • Hosting: Cloudflare Pages project protologue-site, connected to this repo. Every push to main rebuilds and deploys protologue.com automatically.
  • Build command: pip install -r requirements.txt && python3 build.py
  • Output directory: site
  • Domain: protologue.com (DNS on Cloudflare; registration at GoDaddy). AI crawlers are allowed in Cloudflare and in static/robots.txt.
  • Newsletter: Beehiiv (protologue.beehiiv.com). The signup embed lives in data/newsletter-embed.html.
  • MCP server: mcp/ is a Cloudflare Worker (protologue-mcp) at https://mcp.protologue.com/mcp, deployed automatically from this repo. It is listed in the official MCP registry as com.protologue/protologue (mcp/server.json). Registry ownership is proven by static/.well-known/mcp-registry-auth; to re-key, generate a new Ed25519 key and replace that file.
  • Zenodo: GitHub releases are archived on Zenodo automatically, and each one gets a DOI. Put the concept DOI (it resolves to the latest release) in data/doi.txt, and the site adds it to citations, structured data, the data page and llms.txt. Metadata comes from .zenodo.json.
  • Hugging Face: the dataset is mirrored at https://huggingface.co/datasets/franklinpolymathic/protologue (configs terms and categories). Update it when entries change.
  • Kaggle: mirrored at https://www.kaggle.com/datasets/protologue/protologue (the four files from site/data/). Upload a new version when entries change.

Proposed changes arrive as pull requests; merging one publishes it.

Growing citations after launch

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

Protologue: common questions

Is Protologue MCP server safe?
Yes, by our scan: it is graded A (91/100). Read the Protologue safety report
How do I install Protologue?
It runs remotely at mcp.protologue.com. Add it to Claude Code, Cursor, VS Code or Claude Desktop with the snippets above, or call it through the mcp.market gateway without installing anything.
Does Protologue need an API key?
Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is Protologue maintained?
The last commit was 23 days ago (2026-10-12). The latest release is v1.0.0.
Is Protologue up?
100% of our last 28 checks got an answer. We check remote servers about four times a day.
How does Protologue compare with other AI and agents MCP servers?
safety score 91/100 (higher than 88% of 4,460 AI and agents servers); tools 4 (the typical AI and agents server has 6); tools that change things 0% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.