MCP server exposing LogosDB semantic search to Claude Code and other MCP clients
Search the mcprush catalogue of MCP servers. Returns name, what it does, its security grade, its price and its id. The install line comes from install_command, one listing at a time.
ArgumentsA call is made on an account: it counts against an allowance and the publisher sees it, which is why this one asks who you are first.
What it does
This is the marketplace's own server, and the only listing here published by us rather than by somebody else. It answers five questions. **search_servers** finds servers by words in the name or description, optionally inside one category or only the free ones. **get_server** returns everything the catalogue holds about one of them: what it does, the tools it declares and what each reaches, the security grade and the number of findings behind it, and the price. **list_categories** returns every heading with a live count under it. **search_skills** does the same for agent skills. **install_command** returns the exact line to run — or the config block to write, and the file it goes in — for the client the caller is running, and says so plainly where that client cannot run the server at all. It reads the same database the pages read, with SELECTs and nothing else. It holds no credential of yours, writes nowhere, and returns no text from a third party — every string in an answer came out of this catalogue.
Quickstart
# 1 — install (mcprush login holds a key from your dashboard)
npx mcprush@latest add mcprush-catalogue
# 2 — ask your agent something
> Search the mcprush catalogue from your agent: MCP servers and agent skills, with the security grade, the price and the per-client install line for each.
mcprush Catalogue is free: there is no plan to choose, no cap to set and nothing that can bill you.
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. Nothing here runs on your machine — this server runs on the publisher’s own infrastructure behind our gateway, and what you install is the connection to it.
Claude Code has its own MCP command, and the key rides on it as a header — the gateway refuses a call that carries none. Put your key from Access in $MCPRUSH_KEY, or let npx mcprush@latest add mcprush-catalogue write the same entry for you.
claude mcp add --transport http mcprush-catalogue https://mcprush.com/gw/mcprush-catalogue/mcp \
--header "Authorization: Bearer $MCPRUSH_KEY"Reconnect, or start a new session, and the tools appear in the model’s tool list.
One config entry pointing at the gateway. The server itself runs on the publisher’s own infrastructure, so nothing from this listing executes on your machine.
5 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
Search the mcprush catalogue of MCP servers. Returns name, what it does, its security grade, its price and its id. The install line comes from install_command, one listing at a time.
No parameter schema on file.
Everything the catalogue knows about one MCP server: what it does, the tools it declares, its security grade and findings, its price, and the command that installs it.
No parameter schema on file.
The headings the catalogue is filed under, with how many live servers sit in each.
No parameter schema on file.
Search the mcprush catalogue of agent skills — instructions an agent reads rather than servers it calls.
No parameter schema on file.
The exact line to run — or the config block to write — to add one server to one client. Thirteen clients are named and each takes its own form, so this returns the right one rather than a generic package name. Where a client cannot run the server at all, it says so and why.
No parameter schema on file.
- Every tool, 500 calls a month at 60 a minute, and nothing is charged
- A buyer key from your dashboard — the gateway refuses a call without one
- Answers through our gateway, so every call is in your log
- Nothing to cap, because nothing bills
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable. mcprush Catalogue costs nothing to install and nothing to call; past the free tier's allowance a call is refused rather than charged.
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
This listing is a hosted endpoint: the publisher runs it and we connect to it. The scanner reads packages and source, and neither exists to read here, so there is no grade — not a withheld one, an unmeasured one. What can be checked instead is on Installation: what it asks to reach and what it writes.
Release history
Pinned to 1.0.1 — the install command below asks for that release. A pin is part of an install, so it is kept for this visit and written down when you install.
- Checks that the release reads the tool surface from the endpoint rather than from our table.
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Writing one takes an account with at least 50 real tool calls against mcprush Catalogue in the last 90 days. That is the whole gate — there is no other way to post, which is why the counts beside each review are worth reading.
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes an account with 50 real tool calls against it.