Name: Firecrawl
Price: 29 USD
Author: mcpdevpro

Firecrawl MCP Hosted by mcprush

Crawl and scrape the web into clean markdown

Grade A Remote · Streamable HTTP Buyer key + your own key 27 tools v0.1.0 · 6 Sep 2026

No reviews yet by mcpdevpronpm Hosted here, behind our gateway

97/100

trust score

tools declared

remote

via our gateway

—

p95 latency

What it does

Crawl and scrape the web into clean markdown. Built from firecrawl-mcp, Firecrawl's own server, and run on mcprush hosting: there is no endpoint to keep alive and nothing to deploy yourself. It asks for your own Firecrawl API key (Dashboard › Variables), and your calls count against your Firecrawl plan. The image is pinned, so what answers today is what answered yesterday.

Quickstart

# 1 — buy it first ($29 a month): mcprush.com/checkout?server=firecrawl-hosted-mcp
#     a key alone is not enough: the gateway refuses every call until it is bought
# 2 — sign in with a key of the account that bought it: npx mcprush@latest login
#     the key is at mcprush.com/dashboard#access
# 3 — install
npx mcprush@latest add mcpdevpro/firecrawl-hosted-mcp

# 4 — ask your agent for something these tools do
#   firecrawl_scrape, firecrawl_map, firecrawl_search and 24 more

Windows PowerShell says 'running scripts is disabled on this system'? Run Set-ExecutionPolicy -Scope CurrentUser RemoteSigned once, or type npx.cmd instead of npx (codex.cmd, gemini.cmd, grok.cmd likewise). PowerShell 7 needs neither.

PublisherVerified · since 2026

mcpdevpro11 servers

6 categories · publishing since 2026

All 11 servers

Installation

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 infrastructure we host behind our gateway, and what you install is the connection to it.

Claude Codedeclared by this listing

Claude Code has its own MCP command, and the key rides on it as a header — the gateway refuses a call that carries none. Claude Code reads MCPRUSH_KEY each time it connects, so the key stays out of its config: export your key from Access in your shell profile (macOS, Linux), or run setx MCPRUSH_KEY <your key> and open a new terminal (Windows). Or let npx mcprush@latest add mcpdevpro/firecrawl-hosted-mcp write the entry with the key for you; --scope user makes it available in every project. The first connection after a quiet spell starts the server, which takes up to a minute: if your client says it failed to connect, reconnect after that (/mcp in Claude Code).

Buy it first — $29 a month. A key alone is not enough: until this account has bought it, the gateway refuses every call. Subscribe, then use a key of the account that bought it.

claude mcp add --transport http --scope user firecrawl-hosted-mcp https://mcprush.com/gw/firecrawl-hosted-mcp/mcp --header 'Authorization: Bearer ${MCPRUSH_KEY}'

Reconnect, or start a new session, and the tools appear in the model’s tool list.

This is a paid listing: the gateway answers only a key of an account whose subscription to it is active — how the login works. Until then add writes nothing: signed out, it names the price and the checkout link; signed in, it prints the checkout link, or why the subscription is held (ended, paused, an unpaid invoice) and the link that lifts it. The gateway refuses every call the same way, and most clients only show the server as failed.

What it asks of you

It reaches a system of yours, so it needs your own credential rather than the publisher’s: FIRECRAWL_API_KEY — Your Firecrawl API key (starts with fc-), from firecrawl.dev/app/api-keys; a free Firecrawl account has one.. You set it after installing; the value is sealed here and handed to the server when it starts.

What it writes

One config entry pointing at the gateway. The server itself runs on infrastructure we host, so nothing from this listing executes on your machine.

What you approve

27 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.

Only tools that write or reach the network

Retrieve and extract content from one supplied URL through Firecrawl. Use this when the request identifies a page and needs its content or defined fields. It can return markdown, HTML, links, screenshots, branding data, a targeted answer, or JSON matching a supplied schema; JSON is useful when the requested result has defined fields, while markdown preserves readable page content. This tool oper

Parameter	Type	Required	Notes
url	string	yes	—
formats	array	no	—
jsonOptions	object	no	—
queryOptions	object	no	—
screenshotOptions	object	no	—
parsers	array	no	—
pdfOptions	object	no	—
onlyMainContent	boolean	no	—
redactPII	boolean	no	—
includeTags	array	no	—
excludeTags	array	no	—
waitFor	number	no	—
actions	array	no	—
mobile	boolean	no	—
skipTlsVerification	boolean	no	—
removeBase64Images	boolean	no	—
location	object	no	—
storeInCache	boolean	no	—
zeroDataRetention	boolean	no	—
maxAge	number	no	—

Enumerate URLs indexed under one website through Firecrawl without fetching each page's content. Use this when the request asks for a site's URL inventory, when several relevant pages must be located, or when the desired page URL is unknown. An optional search term narrows the URL list, while sitemap, subdomain, query-parameter, and result-limit options control coverage. Returns matching URLs

Parameter	Type	Required	Notes
url	string	yes	—
search	string	no	—
sitemap	string	no	—
includeSubdomains	boolean	no	—
limit	number	no	—
ignoreQueryParameters	boolean	no	—

Search web, news, or image sources and return ranked results. Operators include quoted phrases, -term, site:host, inurl:term, intitle:term, and related:host; the set is non-exhaustive. includeDomains and excludeDomains are mutually exclusive hostname filters; categories limit results to GitHub, research, PDF, or developer sources. For a programming question, add `categories: ["deve

Parameter	Type	Required	Notes
query	string	yes	—
highlights	boolean	no	Return query-relevant highlights for each search result. Set to false to keep the original search snippets.
limit	number	no	—
tbs	string	no	—
filter	string	no	—
location	string	no	—
includeDomains	array	no	—
excludeDomains	array	no	—
sources	array	no	—
categories	array	no	Limit results to specific source types. github searches GitHub repositories, code, issues, and docs; research restricts ordinary web results to research-affiliated websites and returns page snippe
enterprise	array	no	—
scrapeOptions	object	no	—

Records schema-validated quality feedback for a prior firecrawl_search UUID searchId. A good rating requires a valuable source, partial a valuable source or at least one missingContent entry, and bad at least one missingContent entry or a query suggestion; caps are 50 valuableSources and 20 missingContent entries. Eligibility is limited to successful searches within the feedbac

Parameter	Type	Required	Notes
searchId	string	yes	—
rating	string	yes	—
valuableSources	array	no	—
missingContent	array	no	Array of specific pieces of content the agent expected to find but did not. One entry per distinct topic. Each entry has a short topic and optional longer description.
querySuggestions	string	no	—

Submit concise quality feedback for a completed search, scrape, parse, or map job. Provide the endpoint, job ID, rating, and relevant issue codes or small contextual fields; omit large page contents and raw outputs. Returns submission status, feedback ID, and accounting fields.

Parameter	Type	Required	Notes
endpoint	string	yes	—
jobId	string	yes	—
rating	string	yes	—
issues	array	no	—
tags	array	no	—
note	string	no	—
valuableSources	array	no	—
missingContent	array	no	—
querySuggestions	string	no	—
url	string	no	—
pageNumbers	array	no	—
metadata	object	no	—

Start a multi-page crawl at a website URL, poll it to a terminal state, and return the final status and collected data. Scope can be bounded with include/exclude paths, depth, page limit, subdomain/external-link controls, sitemap handling, delay, and scrape options. Crawl results can be large; use conservative limits when full-site coverage is unnecessary. Webhooks and interactive scrape actions

Parameter	Type	Required	Notes
url	string	yes	—
prompt	string	no	—
excludePaths	array	no	—
includePaths	array	no	—
maxDiscoveryDepth	number	no	—
sitemap	string	no	—
limit	number	no	—
allowExternalLinks	boolean	no	—
allowSubdomains	boolean	no	—
crawlEntireDomain	boolean	no	—
delay	number	no	—
maxConcurrency	number	no	—
webhook	string	no	—
webhookHeaders	object	no	—
deduplicateSimilarURLs	boolean	no	—
ignoreQueryParameters	boolean	no	—
scrapeOptions	object	no	—

Retrieve the current status, progress, and available results for an existing crawl ID. This only reads Firecrawl job state and does not start or modify the crawl.

Parameter	Type	Required	Notes
id	string	yes	—

Deprecated compatibility entry point. Use firecrawl_scrape once per known URL with formats: ["json"] and jsonOptions containing the prompt and schema. Use firecrawl_search or firecrawl_agent before Scrape when URLs are not known.

Parameter	Type	Required	Notes
urls	array	yes	—
prompt	string	no	—
schema	object	no	—
allowExternalLinks	boolean	no	—
enableWebSearch	boolean	no	—
includeSubdomains	boolean	no	—

Start an asynchronous web research job from a prompt, optional seed URLs, and an optional JSON schema. Use this for a requested synthesis across multiple sources when the task can wait for asynchronous completion. The agent can search, navigate, read pages, and assemble a structured result. This call returns only a job ID, not the research result. Read the job with firecrawl_agent_status until

Parameter	Type	Required	Notes
prompt	string	yes	—
urls	array	no	—
schema	object	no	—

Retrieve progress or final results for a firecrawl_agent job ID. A processing response is non-terminal and does not contain the final research result. Check again after 15–30 seconds until the status is completed or failed; complex jobs can take several minutes. If the job cannot finish within the task's available time, use firecrawl_search and firecrawl_scrape to complete the request

Parameter	Type	Required	Notes
id	string	yes	—

Open or reuse a live browser session to navigate a page, click controls, fill fields, or run browser code. Provide either url or scrapeId, and either a natural-language prompt or executable code; code can run as Bash, Python, or Node with a bounded timeout. This acts on the live site, so actions such as form submission can create persistent external side effects. Returns execution output

Parameter	Type	Required	Notes
scrapeId	string	no	—
url	string	no	—
prompt	string	no	—
code	string	no	—
language	string	no	—
timeout	number	no	—
scrapeOptions	object	no	—

Stop the live interact session associated with a scrapeId and release its resources. Returns a success confirmation.

Parameter	Type	Required	Notes
scrapeId	string	yes	—

Parse one supported document into markdown, HTML, links, summary, targeted answers, or JSON matching a schema. Supported inputs include common HTML, PDF, Word, RTF, OpenDocument, and spreadsheet files; PDF parsing can be bounded with pdfOptions.maxPages. Local MCP reads filePath from the server filesystem. Hosted MCP uses two calls: first provide filePath to receive upload instructions, up

Parameter	Type	Required	Notes
formats	array	no	—
jsonOptions	object	no	—
queryOptions	object	no	—
parsers	array	no	—
pdfOptions	object	no	—
onlyMainContent	boolean	no	—
redactPII	boolean	no	—
includeTags	array	no	—
excludeTags	array	no	—
removeBase64Images	boolean	no	—
skipTlsVerification	boolean	no	—
storeInCache	boolean	no	—
zeroDataRetention	boolean	no	—
maxAge	number	no	Ignored: parse never reuses or stores indexed content.
proxy	string	no	—
filePath	string	yes	Absolute or relative path to a local file to parse. Supported: .html, .htm, .pdf, .docx, .doc, .odt, .rtf, .xlsx, .xls
contentType	string	no	Optional MIME type override. If omitted, the server infers the file kind from the extension.

Create a recurring scrape, crawl, or search monitor that compares each check with its retained predecessor. The simple form accepts page/pages or queries plus a plain-language goal; the advanced body form controls targets, schedule, change-tracking formats, judging, retention, webhook, and notifications. In the simple form, a goal is required. If queries contains one or more non-em

Parameter	Type	Required	Notes
body	object	no	—
page	string	no	—
pages	array	no	—
queries	array	no	—
searchWindow	string	no	—
maxResults	integer	no	—
includeDomains	array	no	—
excludeDomains	array	no	—
goal	string	no	—
name	string	no	—
scheduleText	string	no	—
timezone	string	no	—
email	string	no	—
includeDiffs	boolean	no	—
webhookUrl	string	no	—

List monitors for the authenticated account with optional pagination controls. Returns one page of monitor records and pagination metadata.

Parameter	Type	Required	Notes
limit	integer	no	—
offset	integer	no	—

Retrieve one monitor by ID, including its configuration and current state. This does not run or modify the monitor.

Parameter	Type	Required	Notes
id	string	yes	—

Patch an existing monitor by ID. The body can change its name, active/paused status, schedule, targets, goal, judging, webhook, notifications, or retention; these changes affect future scheduled checks. Returns the updated monitor.

Parameter	Type	Required	Notes
id	string	yes	—
body	object	yes	—

Permanently delete a monitor by ID and stop its future schedule. This operation cannot be undone and returns deletion status.

Parameter	Type	Required	Notes
id	string	yes	—

Queue an immediate check for a monitor outside its normal schedule. This starts network work for the monitor's configured targets and returns the queued check.

Parameter	Type	Required	Notes
id	string	yes	—

List historical checks for a monitor, optionally filtered by status and bounded by a result limit. Returns one page of check summaries and pagination metadata.

Parameter	Type	Required	Notes
id	string	yes	—
limit	integer	no	—
offset	integer	no	—
status	string	no	—

Retrieve one monitor check and its page-level results, optionally filtered by page status. Pages report same, new, changed, removed, or error; configured goal judging can add a meaningful-change decision. Markdown tracking returns a unified text diff, JSON tracking returns field paths with previous/current values and a current snapshot, and mixed tracking returns both. Returns one page

Parameter	Type	Required	Notes
id	string	yes	—
checkId	string	yes	—
limit	integer	no	—
skip	integer	no	—
pageStatus	string	no	—

Search paper metadata and abstracts with a natural-language query across the indexed corpus, which spans biomedical, life-science, and clinical literature (PubMed, bioRxiv, medRxiv) alongside arXiv and other scientific sources. Optional author, category, and date filters constrain results. Several distinct framings of the same question surface different papers than a single query does. Returns

Parameter	Type	Required	Notes
query	string	yes	Natural-language research topic or question, including methods, systems, conditions, populations, interventions, or outcomes when relevant.
k	integer	no	Number of ranked papers to return (default 40).
authors	array	no	Author substring filter(s); ALL must match (case-insensitive).
categories	array	no	Paper category filter(s) (e.g. cs.LG); ALL provided values must match.
from	string	no	Inclusive lower bound on created/updated date (YYYY-MM-DD).
to	string	no	Inclusive upper bound on created/updated date (YYYY-MM-DD).

Retrieve canonical metadata for one paper ID, such as an arXiv, PMC, PMID, or DOI identifier. Returns the title, abstract, authors, categories, source IDs, and dates as markdown.

Parameter	Type	Required	Notes
paperId	string	yes	Canonical paperId or primaryId such as arxiv:1706.03762, pmcid:PMC12530322, pmid:40953549, or doi:10.1016/j.neunet.2025.108095.

Find citation-graph candidates from one to ten seed_ids; the first ID is the primary seed and later IDs are anchors. mode defaults to similar (co-citation/bibliographic coupling); citers returns papers citing a seed and references papers cited by a seed. intent ranks candidates. Returns ranked candidates and the evaluated pool size.

Parameter	Type	Required	Notes
seed_ids	array	yes	—
intent	string	yes	—
mode	string	no	—
k	integer	no	—
rerank	boolean	no	Apply an additional rerank over the fused candidates.

Retrieve in-body passages from one paper that are relevant to a specific question. Full text is available only for indexed papers; k controls the number of passages. Returns matching passages or a notice when full text is unavailable.

Parameter	Type	Required	Notes
paperId	string	yes	Canonical paperId or primaryId such as arxiv:1706.03762, pmcid:PMC12530322, pmid:40953549, or doi:10.1016/j.neunet.2025.108095.
question	string	yes	—
k	integer	no	Number of passages to return (default 4).

Search indexed public GitHub issue, pull-request, and README content. Returns ranked matches with repository, URL, snippet, and full matched markdown when available.

Parameter	Type	Required	Notes
query	string	yes	—
k	integer	no	—

For a developer question — code behaviour, a library or framework, an API contract, an error message, or a known bug — search an index built for coding agents. The index covers GitHub issues, merged pull requests, repository READMEs, and curated documentation sites. Set skills to "only" to limit the search to agent-skill files. Returns ranked results with an ID, source type, URL, title, and the

Parameter	Type	Required	Notes
query	string	yes	Natural-language developer question or search phrase, including the library, error message, or API involved when relevant.
k	integer	no	Number of ranked results to return (default 10).
skills	string	no	Set to "only" to search only agent-skill files.

Starter

$29 / month

50,000 calls a month, included
120 calls a minute at peak
Every tool the listing has
Cancel any time — the unused days are credited
Runs behind the gateway, so cancelling stops it

What counts against the 50,000 calls a month on Starter

Tool	Unit	Calls used	Out of the monthly allowance
firecrawl_scrape	write	2	0.0040%
firecrawl_map	call	1	0.0020%
firecrawl_search	call	1	0.0020%
firecrawl_search_feedback	write	2	0.0040%
firecrawl_feedback	write	2	0.0040%
firecrawl_crawl	write	2	0.0040%
firecrawl_check_crawl_status	call	1	0.0020%
firecrawl_extract	call	1	0.0020%

Failed calls, timeouts and anything the gateway rejects never count. When the allowance runs out the gateway returns an error naming the plan limit — nothing is billed beyond the subscription, ever.

ATrust score 97 / 100

Scanned: 3.30.0 · 14 Oct 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 score97

Findings0 threat · 1 capability

Capabilitymoderate

Coveragesource

Verificationsource

Surface digesta298e6135c5050ea632231db10eb656f27270e923ae710b1600de20f8db25717

Score vectorthreat 100 → client 97

Term	Level	What it prices	Points
capability-exposure	moderate	capability blast radius (moderate) — client exposure if the model is manipulated	−3
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 (30 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 30 recovered tools are registered only when !SEARCH_FEEDBACK_DISABLED && !isLocalKeylessStartup() holds (dist/index.js:4893) — 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 28.

1 of the 30 recovered tools are registered only when alexandriaFeedbackAvailable() holds (dist/index.js:5012) — 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 28.

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. moderate is the level these add up to.

28 tools are registered unconditionally · (1) 1 more only when !SEARCH_FEEDBACK_DISABLED && !isLocalKeylessStartup() holds (dist/index.js:4893) · (2) 1 more only when alexandriaFeedbackAvailable() holds (dist/index.js:5012) — typically when a key or option is configured. All 30 are in the table below and were analysed; the conditional ones are marked.

Tool	Capability tags	Why the tag was assigned
firecrawl_developer_search	no tags
firecrawl_gov_search	untrusted-input	untrusted-input: declares openWorldHint: true (interacts with entities outside the server)
firecrawl_monitor_create	external-sink	external-sink: keyword "webhook"
firecrawl_monitor_list	no tags
firecrawl_monitor_get	no tags
firecrawl_monitor_update	no tags
firecrawl_monitor_delete	no tags
firecrawl_monitor_run	no tags
firecrawl_monitor_checks	no tags
firecrawl_monitor_check	no tags
firecrawl_research_search_papers	no tags
firecrawl_research_inspect_paper	no tags
firecrawl_research_related_papers	no tags
firecrawl_research_read_paper	no tags
firecrawl_research_search_github	untrusted-input	untrusted-input: declares openWorldHint: true (interacts with entities outside the server)
firecrawl_credit_usage	no tags
firecrawl_scrape	untrusted-inputexternal-sink	untrusted-input: keyword "scrape"; external-sink: handler sends an HTTP POST ( client.http.post("/v2/scrape") at dist/index.js:4697, handler sends an HTTP POST (fetch(${resolveApiBaseUrl()}${path2}) at dist/index.js:4800
firecrawl_map	no tags
firecrawl_search	untrusted-inputexternal-sink	untrusted-input: keyword "search web", declares openWorldHint: true (interacts with entities outside the server); external-sink: handler sends an HTTP POST (fetch(${resolveApiBaseUrl()}${path2}) at dist/index.js:4800
firecrawl_find_tools	untrusted-inputexternal-sink	untrusted-input: keyword "browse"; external-sink: handler sends an HTTP POST ( client.http.post("/v2/scrape") at dist/index.js:4697
firecrawl_search_feedback conditional (1)	external-sink	external-sink: handler sends an HTTP POST (fetch(endpoint) at dist/index.js:4970
firecrawl_feedback conditional (2)	external-sink	external-sink: handler sends an HTTP POST (fetch(${apiBase}/v2/feedback) at dist/index.js:5109
firecrawl_crawl	untrusted-inputexternal-sink	untrusted-input: keyword "scrape"; external-sink: handler sends an HTTP POST ( client.http.post("/v2/crawl") at dist/index.js:5200
firecrawl_check_crawl_status	untrusted-input	untrusted-input: keyword "crawl"
firecrawl_extract	untrusted-input	untrusted-input: declares openWorldHint: true (interacts with entities outside the server)
firecrawl_agent	no tags
firecrawl_agent_status	no tags
firecrawl_interact	no tags
firecrawl_interact_stop	external-sink	external-sink: handler sends an HTTP DELETE ( client.http.delete(/v2/scrape/${encodeURIComponent(scrapeId)}/interact) at dist/index.js:5564
firecrawl_parse	external-sink	external-sink: handler sends an HTTP POST (fetch(endpoint) at dist/index.js:5639, handler sends an HTTP POST (fetch(${resolveApiBaseUrl()}${pathName}) at dist/index.js:4356, handler sends an HTTP POST (fetch(${resolveApiBaseUrl()}${path2}) at dist/index.js:4800

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 digesta298e6135c5050ea

Scanned2026-10-14

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.