Brave Search MCP Server: web results, images, videos, rich results, AI summaries, and more.
Nothing to run from here
API Anything is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
94/100
trust score
602
downloads a day
local
runs on your machine
5k
downloads in 30d
What it does
Call websites as APIs: a shared catalog of operations learned from each site's own requests.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user api-anything-mcp '--' npx -y api-anything mcp
# 2 — ask your agent for something these tools do
# list_sites, find_sites, list_operations and 8 more
API Anything costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
GOAll 1 server
goodnight0001 server
1 category
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. This one runs on your machine: your client starts API Anything as a process under your own user, with your files and your network, so the tool surface below is what it can do to your computer rather than to a server somewhere else. Its scan result is on the Security tab — read the surface before you approve it.
Claude Codedeclared by this listing
This is a public server: you run it yourself and this marketplace is not in the path. You need Node.js — the current LTS (24) is the safe choice; npx comes with it. Claude Code registers it in one command; --scope user makes it available in every project. The '--' is in quotes so that PowerShell passes it on.
claude mcp add --scope user api-anything-mcp '--' npx -y api-anything mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
Free on mcprush, and it runs from its publisher’s own package: this marketplace is not in the path, so there is no key of ours to hold and no card to add.
What it asks of you
Nothing is required, but it can take API_ANYTHING_HOME (Directory for learned sites, sessions and settings. Defaults to ~/.api-anything.), API_ANYTHING_BROWSER (Chromium browser used to learn sites and for the browser tier, by name (brave) or path. Defaults to Google Chrome.) if you want to set them.
What it writes
One config entry your client uses to start the process locally. A local server runs with your file system and your network, which is why it is priced without metering.
What you approve
11 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.
Read from its source code. A server that builds its tool list when it starts can list more tools than this.
List the websites api-anything can call, with how many operations each has.
No parameter schema on file.
Find websites someone already turned into operations: the shared registry and this machine's sites, best match first. Each op has params, matched/unmatched query words and separate registry health and local verification (unknown without evidence). Partial lexical matches do not guarantee the…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | string | yes | words, a domain or a URL |
List a site's operations, each with a JSON Schema of its args (inputSchema), output cardinality and field type hints (unknown when not recorded), links to other operations, and the site's notes. Call this before call_operation. An uninstalled shared site is pulled first (reads only). To prepare a…
No parameter schema on file.
Call a site's read operation. For a site from find_sites, first check its match's domain is the site the user means. To watch something (new posts, a price), pass changes or changesOnly: changes {since, added, removed, changed, unchanged} compare with the previous ok answer for the same args,…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| site | string | yes | — |
| op | string | yes | operation name from list_operations |
| args | object | no | param name -> value |
| view | object | no | — |
Call up to 20 reads of installed sites, with ordered results. Use list_operations first (it pulls missing sites); check each site's domain is the one the user means. Takes items {id?, site, op, args?}; missing ids are 1-based positions. Returns {ok, results: [{id, site, op, ...callResult}]}.…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| items | array | yes | — |
| concurrency | integer | no | — |
Read or reshape a kept extracted answer locally, without requesting the site. Pass more unchanged to continue, or resultId and fields/maxChars to reproject from the start. offset counts items; with format json it counts characters and data is a JSON fragment (encoding json): concatenate fragments,…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| resultId | string | yes | — |
| offset | integer | no | — |
| format | string | no | — |
Call a site's write operation (list_operations marks it write: true). A write changes the user's account: only call it when the user asked for that exact action. A write's write says what it did: not_sent, not_applied, accepted, applied (its readback found it) or may_have_applied; never send one…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| site | string | yes | — |
| op | string | yes | a write operation's name from list_operations |
| args | object | no | param name -> value |
| view | object | no | — |
| again | boolean | no | — |
| idempotencyKey | string | no | — |
Wait up to about 25 s for a job a tool answered class pending with, and return its result, or pending again while it runs. It never runs the call again. A finished job's result is kept for 15 minutes.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| job | string | yes | the job id from a pending answer |
This machine's record of how a site's operations have been doing, from local files only (nothing is sent): a cool-down, stale marks, the tier calls start at beside the op's own, the last heal and verify, writes of the last 24 h, and calls of the last 24 h and 7 days (count, ok rate, tiers, median…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| site | string | no | site name from list_sites |
Sign in to a site so its operations work; use after a call returns class 'auth'. mode 'import' (default) refreshes the session from the browser profile the user already chose with api-anything login (no password); 'window' opens a visible browser for the user to sign in and clear 2FA/captcha by…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| site | string | no | site name from list_sites |
| url | string | no | a full URL, if the site is not yet known (window mode only) |
| mode | string | no | — |
| Parameter | Type | Required | Notes |
|---|---|---|---|
| trigger | string | yes | the page URL with {param} placeholders, e.g. https://site.com/search?q={q} |
| args | object | yes | the user's own values, by param name: their answer comes back in data |
| args2 | object | yes | another real value of the same kind, chosen by you: it becomes the shared example |
| args3 | object | yes | a third real value, different from both: the check that the operation works |
| site | string | no | site name; default: the trigger's host |
| op | string | no | a camelCase operation name, e.g. searchBooks; default: from the URL path |
| intent | string | no | what the operation is for, in general words (it is shared): 'search books by title' |
| pickRequest | integer | no | a request id from chosen or alternatives |
| extract | string | no | a path into a JSON answer: data.items, sections[*].items |
| pick | array | no | fields kept per item; name=path renames |
| html | object | no | — |
| embedded | string | no | a regex for JSON inside the page; group 1 marks where it starts |
| captures | array | no | an earlier result's captures: learn again from them, with no browser |
| fresh | boolean | no | — |
| write | boolean | no | not supported: writes are learned with the CLI |
| steps | array | no | — |
| paging | no | — |
Free
$0 forever
- Every tool, no call limit
- No card, and mcprush charges nothing for it
- Source published under MIT
- Runs on your machine — nothing of it reaches our gateway
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install API Anything or to call it, at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: —
ATrust score 94 / 100
Release 0.4.0 · scanned 6 Nov 2026
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.
Threat score100
Client score94
Findings6 threat · 2 capability
Capabilityhigh
Coveragesource
Verificationsource
Surface digestcce2556ed6fe7d31cabcf12804123705414da7dd41615adddb6963bf6485eace
Score vectorthreat 100 → client 94
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | high | capability blast radius (high) — client exposure if the model is manipulated | −6 |
| verification-discount | source | publisher verification (provenance) — cryptographic build provenance ties the artifact to its source | −0 |
| coverage-honesty | source | inspection depth (source) — how much of the target the scan could see | −0 |
score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
Tool surfaceread
Implementation sourceread
Package metadataread
Live transportnot available
Tools were statically extracted from the published source (11 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".
1 of the 11 recovered tools are registered only when !learnTool.enabled is false (dist/mcp-learn.js:27) — typically when a key or option is configured. They are part of the server's surface and were analysed; a server started without that configuration exposes only the other 9.
1 of the 11 recovered tools are registered only when allowWrites holds (dist/mcp.js:644) — typically when a key or option is configured. They are part of the server's surface and were analysed; a server started without that configuration exposes only the other 9.
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. high is the level these add up to.
9 tools are registered unconditionally · (1) 1 more only when !learnTool.enabled is false (dist/mcp-learn.js:27) · (2) 1 more only when allowWrites holds (dist/mcp.js:644) — typically when a key or option is configured. All 11 are in the table below and were analysed; the conditional ones are marked.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| learn_site conditional (1) | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| list_sites | no tags | |
| find_sites | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| list_operations | no tags | |
| call_operation | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| call_batch | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| get_result | no tags | |
| call_write_operation conditional (2) | external-sink | external-sink: declares readOnlyHint: false, destructiveHint: true, openWorldHint: true |
| get_job | no tags | |
| site_status | no tags | |
| login | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
flow-1
Untrusted input can drive an external action even though no sensitive source is exposed.
Supply chain and provenance
Integrityfirst-seen
Surface digestcce2556ed6fe7d31
Scanned2026-11-06
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
Always latest — the install command names no version, so it installs the newest release when it runs; the current release on file is 0.4.0. Pin a release below and the command asks for exactly that one.
0.4.0
undated
latestNo release note was published with this version.
—
no reviews yet
Who can review
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.
Sign in to write one
Any signed-in account that does not publish API Anything can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
No reviews yet
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 a signed-in account that does not publish it, and nothing else.