
RyRank
io.github.trigeochiralPublished by GitHub account trigeochiralv1.0.0Updated Oct 24, 2026
Cohere-compatible pay-per-call reranker, no signup, x402/USDC
The publisher's own server: Rank Fast
Overview
Lets an assistant rerank documents by relevance to a query through a hosted, Cohere-compatible pay-per-call API.
- What you can do
- Exposes a single rerank tool that scores and reorders a list of documents against a query, returning a Cohere-compatible response shape of index and relevance_score pairs. The README says it is a hybrid reranker aimed at narrowing retrieval candidate sets, deduping and triage rather than fine semantic disambiguation. The same hosted API also accepts Cohere v2 and Voyage request shapes, so existing rerank client code can point at it with a base URL override.
- When to use it
- Useful when an assistant needs to reorder RAG retrieval results, document shortlists or tool candidates by relevance, especially at high volume where latency and per-call cost matter. Less suited to distinguishing near-identical phrasings.
- Requirements
- Runs as a local stdio process installed from the PyPI package ryrank-mcp (pip or uvx). Requires network access to the hosted API and the RYRANK_API environment variable, which defaults to the provider's base URL. No signup or account is declared.
Installation
In SourceWeft
- Open RyRank in the dashboard and add it to a workspace.
- Enable the server for the chats that should use its tools.
Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.
Other MCP clients
Follow the launch instructions in the repository.
README
RyRank — MCP server
A Cohere-compatible reranker, pay-per-call in USDC on Base (x402), free tier, no signup.
Hosted API: https://trigeochiral.com — set it as RYRANK_API.
Tool
Why
A hybrid reranker, not a cross-encoder: strong when the candidates already share vocabulary with the query, which is the common case for RAG retrieval output and document/tool shortlists. Built for high-volume, latency- and cost-sensitive reranking — narrowing a retrieval candidate set, deduping, triage — rather than close semantic disambiguation between near-identical phrasings. Pay-per-call and about half the price is the trade for that.
Verified against the real cohere.Client, cohere.ClientV2 and voyageai.Client SDKs:
point base_url at this API and existing rerank code runs unmodified.
Install
or with uvx (no install):
Optional: RYRANK_XPAYMENT = a base64 x402 X-PAYMENT payload, to make paid calls past the
free tier. Without it you get 25 free calls/day per IP.
Direct HTTP (no MCP)
Also speaks the exact Cohere v2 (POST /v2/rerank) and Voyage (POST /voyage/v1/rerank) request
and response shapes, so their official SDKs work unmodified with just a base_url override — see
https://trigeochiral.com for details.
License
MIT
Source: README.md at commit 213bbf4
Tools
0Version history
1- v1.0.0LatestSep 16, 2026
Score
50% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
- Reached in the last 30 days25 pts
Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.
- Auth declared10 pts
Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.
- Tools listed15 pts
Answer tools/list without a credential, or ship a package that starts in a sandbox without one.
- DescriptionRequired15 pts
- Logo10 pts
- Documentation15 pts
- License10 pts
Other Rank integrations
Rank Fast
fast.rankOfficial publisher
Remote Rank Fast MCP server that lets an assistant check Google indexing with diagnosis, pull autocomplete keyword ideas, and review AI visibility and guest…

dep-rank
Published by GitHub account j7an
Ranks the GitHub repositories that depend on a given project by stars or a trust heuristic, and searches code across those dependents.

AIWiseRank
Published by GitHub account VLCODE87
A remote MCP server that lets an assistant search, rank and compare AI tools by real web traffic, with pricing, free plans, alternatives and LLM API benchmarks.

Mcp Local Rank Map Pack Tracker
com.mambabuilt
Local MCP server that checks Google organic, map pack and local finder rankings for keywords in specified locations via an Apify actor.
CreceRank
com.crecerank
Remote MCP server that reports how a brand appears in AI assistants such as ChatGPT, Gemini, Perplexity and AI Overviews, with mentions, sources and GEO tips.