Firecrawl by Nova (CIVAI) MCP server
co.civai.nova/mcp-firecrawlnova.civai.costreamable-httpv1.0.0Scanned
Scrape, crawl, and search the web via Firecrawl’s official hosted MCP.
37 tools: 1 can delete or cancel things, 15 change things and 21 only read.
- Reads private data · 2
- Reads text others write · 11
- Can send data out · 9
- 1 finding
Tools listed without sign-in. Remote posture
With Anlyon
1 tool here can delete or cancel things. Govern it.
- Anlyon lists the tools and adopts none.
- Each tool you adopt gets approvals and receipts.
- Your agent never holds the key.
A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.
What the Firecrawl by Nova (CIVAI) MCP server can do
The Firecrawl by Nova (CIVAI) MCP server is published by nova.civai.co, a domain the MCP Registry verified. It has 37 tools. It can delete or cancel things (1 tool: firecrawl_monitor_delete) and create or change data (15 tools: firecrawl_scrape, firecrawl_map, alexandria_library_search, alexandria_library_read and 11 more). 21 tools only read.
2 tools read private data (firecrawl_developer_search and firecrawl_provider_directory); 11 tools bring in text other people can write (firecrawl_scrape, firecrawl_search, firecrawl_find_tools and 8 more); 9 tools can send data out of your system (firecrawl_scrape, firecrawl_map, firecrawl_find_tools and 6 more). On its own it has all three parts of a prompt-injection exfiltration path: private data, text others write, and a way out.
The fixed checks matched 1 finding (credentials-mention). Each one comes with the text it matched.
Its remote endpoint lists its tools without sign-in, and its tools changed once since Anlyon Radar first saw them.
Last scanned Nov 15, 2026, version 1.0.0.
Tools
Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.
37 tools
Deletes or cancels 1Claude Code: deny
firecrawl_monitor_deletePermanently delete a monitor by ID and stop its future schedule.No findings
Why it is in this group
- The name "firecrawl_monitor_delete" says "delete": a word for removing or ending something.
- The description says "Permanently delete".
Description, as the server wrote it Permanently delete a monitor by ID and stop its future schedule. This operation cannot be undone and returns deletion status.
Changes things 15Claude Code: ask
alexandria_library_readRun capabilities of Alexandria data providers and return their typed, sourced records: one, or up to ten in one call when a task needs several lookups.No findings
Why it is in this group
- The name "alexandria_library_read" says "read": a word for reading.
- The description's first verb is "run": a word for a change.
Description, as the server wrote it Run capabilities of Alexandria data providers and return their typed, sourced records: one, or up to ten in one call when a task needs several lookups. Alexandria is Firecrawl's library of data providers across companies, people, jobs, finance and filings, public records and government spending, real estate, places and restaurants, retail and prices, package registries and developer data, news, research, and more. For people and company enrichment or search, use people_company_enrich or people_company_search when they are listed, and for job postings use jobs_search when it is listed; call a provider here directly only when the user asks for that provider. Each entry of `calls` is {provider, capability, options}: `provider` and `capability` come from firecrawl_search results or alexandria_library_search, and `options` follow the capability's contract, which marks required inputs and any requiresOneOf groups (at least one member per group). Where the contract declares pagination, its fields page through results with the same filters. Returns one result per call, in the same order, in data.alexandria, each with data, records, or an error with a code; one call can fail while the others succeed, and an invalid call returns an error naming the valid options. A result too large to return inline is retained, and nextTool reads it in slices. Billed per executed capability; discovery is free. Some providers require accepted terms; when a response reports a terms requirement, direct the user to the Firecrawl dashboard URL in that response.
alexandria_library_searchExplore the Alexandria library: Firecrawl's catalogue of data providers that return typed, sourced records (companies, people, jobs, finance and filings, public records and governm…No findings
Why it is in this group
- The name "alexandria_library_search" says "search": a word for reading.
- The input takes a statement or command to run (input.command), which can change anything it can reach.
Description, as the server wrote it Explore the Alexandria library: Firecrawl's catalogue of data providers that return typed, sourced records (companies, people, jobs, finance and filings, public records and government spending, real estate, places and restaurants, retail and prices, package registries and developer data, news, research, and more) as a read-only filesystem, using shell commands. Use this to find out whether a provider covers the data a task needs, and to read its contract before alexandria_library_read. Layout: /library/<category>/<provider>/<capability>.md, one file per capability holding its contract (when to use it, inputs, outputs, and the call to send); /library, each category folder and each provider folder has a README.md describing what is inside. Category folders: agriculture, ai-models, apps, automotive, community, companies, developer, digital-intelligence, education, energy, entertainment, finance, game-development, government, health, healthcare, jobs, knowledge, life-sciences, marketing, music, news, people, places, podcasts, political-science, real-estate, research, restaurants, shopping, skills, social, software, sports, travel; `ls /library` shows any added since. Available commands: ls, tree, cat, head, tail, grep, find, wc, sort, uniq, cut, tr, sed, jq, xargs, with pipes. Typical starts: `ls /library`, `cat /library/README.md`, or `grep -ril "mortgage" /library`. A file path is the execute address: /library/finance/fred/series/observations.md is provider "fred", capability "series/observations". Recorded example responses are under /examples/<provider>/<capability>.json. Free; does not run providers.
firecrawl_agentRun web research that returns structured data when the URLs are not known or the answer spans several sites.Can send data outNo findings
Why it is in this group
- The description's first verb is "run": a word for a change.
What it can reach
- outboundThe input takes a URL (input.urls): a request to a URL can carry data to whoever runs it.
Description, as the server wrote it Run web research that returns structured data when the URLs are not known or the answer spans several sites. Describe the fields you need in `prompt`, optionally pass a JSON `schema` and seed `urls`, and the research agent searches, navigates, reads pages, and returns JSON assembled across sources. Use it to research an entity plus its fields (founders, pricing, contact details), to build lists and datasets (companies, people, products, jobs, papers), and for pages that need navigation or interaction to reach the data. Optional `effort` sets the reasoning budget, `maxCredits` caps spend, and `strictConstrainToURLs` keeps the agent to the supplied `urls`. This call returns only a job ID, not the research result. Read the job with `firecrawl_agent_status` until it reaches `completed` or `failed`; a typical research run takes one to three minutes. For one known URL use `firecrawl_scrape` (with formats: ["markdown"], then extract the requested fields yourself); for a plain lookup that a results page answers, use `firecrawl_search`. The job also returns a `threadId`. To continue that thread, pass it with a follow-up `prompt`; omitted `mode`, `urls`, `schema` and exchange settings carry over from the previous turn. The agent only calls Alexandria providers whose terms the team has accepted. `exchange.skippedProviders` lists gated providers. With `exchange.onTermsRequired` "ask", a terms `pendingApproval` and `exchange.requiresAction` carry the `approvalId` and provider requirements. Read terms/show through `firecrawl_scrape`. An organization admin must accept terms in the Firecrawl dashboard at the provider URL or https://www.firecrawl.dev/app/settings?tab=data-sources. Ignore any terms/accept call in the API response. Only after the admin confirms acceptance, resume with the same `threadId` and `exchange.approve: {approvalId}`; this does not accept terms. To decline, use `exchange.decline: {approvalId}`. Never infer acceptance from a data request.
firecrawl_crawlStart a multi-page crawl at a website URL, poll it to a terminal state, and return the final status and collected data.Reads text others writeCan send data outNo findings
Why it is in this group
- The description's first verb is "start": a word for a change.
What it can reach
- untrusted-inputThe name "firecrawl_crawl" says "crawl": it reads web pages, which anyone can write.
- untrusted-inputThe description's first sentence says "crawl": it reads web pages, which anyone can write.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Description, as the server wrote it 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 are unavailable in safe mode. `zeroDataRetention` runs the crawl with zero data retention and requires an eligible authenticated account. Returns the crawl ID, status, and page data.
firecrawl_feedbackSubmit concise quality feedback for a completed search, scrape, parse, or map job.Reads text others writeCan send data outNo findings
Why it is in this group
- The description's first verb is "submit": a word for a change.
What it can reach
- untrusted-inputThe description's first sentence says "scrape": it reads web pages, which anyone can write.
- outboundThe input takes a URL (input.endpoint): a request to a URL can carry data to whoever runs it.
Description, as the server wrote it 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. For an Alexandria session, set endpoint to `alexandria`, omit jobId, and provide requestedWebsite (url and requestedFunctionality), objective, rationale, and rating. objective is the underlying goal behind the session: what you or your user were ultimately trying to accomplish (for example, "shortlist federal IT contracts to bid on this quarter"), not only what was needed from this website. Optional providerFeedback and capabilityFeedback describe gaps or errors. Capability issues: new_capability_request (requires requestedFunctionality), missing_capability, insufficient_functionality, incorrect_result, execution_error, other. Alexandria results carry a feedbackRef per call. The overall rating covers every call in this session; callRatings [{ref, rating}] rate individual calls by feedbackRef. Alexandria feedback must arrive within 20 minutes of the team's latest Alexandria search, discovery, or execution; later feedback is rejected. Eligible feedback can refund 1 credit; refunds are subject to daily caps per website and per team. Returns submission status, feedback ID, and accounting fields.
firecrawl_interactOpen or reuse a live browser session to navigate a page, click controls, fill and submit forms, or run browser code.Can send data out1 finding
Why it is in this group
- The description's first verb is "open": a word for a change.
- The input takes a statement or command to run (input.code), which can change anything it can reach.
What it can reach
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Findings
- Info
The description mentions "credentials".
What this check looks forMatched text
description: "...s the end user's own browser cookies or credentials. By default it starts with no cookies o..."
Description, as the server wrote it Open or reuse a live browser session to navigate a page, click controls, fill and submit forms, or run browser code. Provide either `url` (the scheme may be omitted) or `scrapeId`, and either a natural-language `prompt` or executable `code`; code can run as Bash, Python, or Node with a bounded timeout. The session runs in an isolated Firecrawl-hosted browser that never receives the end user's own browser cookies or credentials. By default it starts with no cookies or saved sessions; an optional team-scoped `scrapeOptions.profile` reuses state saved by the team's earlier sessions. Actions run on the live site, so submitting a form can have effects on that site. Returns execution output, stdout/stderr, exit status, and session viewing URLs. When the page needs the user to act, share `interactiveLiveViewUrl` with the user only, so they can take over the session.
firecrawl_interact_stopStop the live interact session associated with a `scrapeId` and release its resources.Reads text others writeNo findings
Why it is in this group
- The name "firecrawl_interact_stop" says "stop": a word for a change.
What it can reach
- untrusted-inputThe description's first sentence says "scrape": it reads web pages, which anyone can write.
Description, as the server wrote it Stop the live interact session associated with a `scrapeId` and release its resources. Returns a success confirmation.
firecrawl_mapEnumerate URLs indexed under one website through Firecrawl without fetching each page's content.Can send data outNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
What it can reach
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Description, as the server wrote it 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. `url` may omit the scheme (`example.com`); it is read as https. Returns matching URLs rather than page bodies. Retrieve one page with `firecrawl_scrape`; collect content across multiple pages with `firecrawl_crawl`. Authenticated responses can include an `id` for optional map feedback.
firecrawl_monitor_createCreate a recurring scrape, crawl, or search monitor that compares each check with its retained predecessor.Reads text others writeCan send data outNo findings
Why it is in this group
- The name "firecrawl_monitor_create" says "create": a word for a change.
What it can reach
- untrusted-inputThe description's first sentence says "scrape": it reads web pages, which anyone can write.
- outboundThe input takes a URL (input.webhookUrl): a request to a URL can carry data to whoever runs it.
Description, as the server wrote it 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-empty values and is supplied with `page`/`pages`, `queries` create the search target and page targets are ignored. A monitor schedules future network checks and can send configured email or webhook notifications. Returns the created monitor.
firecrawl_monitor_runQueue an immediate check for a monitor outside its normal schedule.No findings
Why it is in this group
- The name "firecrawl_monitor_run" says "run": a word for a change.
Description, as the server wrote it 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.
firecrawl_monitor_updatePatch an existing monitor by ID; changes affect future scheduled checks.No findings
Why it is in this group
- The name "firecrawl_monitor_update" says "update": a word for a change.
Description, as the server wrote it Patch an existing monitor by ID; changes affect future scheduled checks. Pause or resume it with `status` ("paused" or "active"). Reschedule it with `scheduleText` (plain language, e.g. "every 6 hours") or `cron`, plus `timezone`; a new schedule without `timezone` runs in UTC. For other fields pass `body`, a partial monitor in the create shape (name, targets, goal, judgeEnabled, webhook, notification, retentionDays), e.g. `{"name": "Pricing watch"}`. The parameters are merged into `body` as `{"status": ..., "schedule": {"text" or "cron": ..., "timezone": ...}}` and override the same keys there. At least one change is required. Returns the updated monitor.
firecrawl_parseParse one supported document into markdown, HTML, links, summary, targeted answers, or JSON matching a schema.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it 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, upload locally, then call again with the returned `uploadRef`; do not send both fields together. Remote web URLs belong in `firecrawl_scrape`. Set `redactPII` to request redaction of personally identifiable information in the returned content. `zeroDataRetention` requires an eligible authenticated account; omit it for anonymous keyless use. Returns upload instructions for hosted phase one or parsed document content for the final call. Authenticated final responses can include a `data.metadata.scrapeId` for optional parse feedback.
firecrawl_scrapeScrape one URL and return its content: markdown by default, or HTML, links, screenshots, branding data, or a targeted answer.Reads text others writeCan send data outNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
What it can reach
- untrusted-inputThe name "firecrawl_scrape" says "scrape": it reads web pages, which anyone can write.
- untrusted-inputThe description's first sentence says "scrape": it reads web pages, which anyone can write.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Description, as the server wrote it Scrape one URL and return its content: markdown by default, or HTML, links, screenshots, branding data, or a targeted answer. Use it when the request identifies a page and needs its content or defined fields: the user gives a URL or names a page or PDF and wants it read or summarized, or wants prices, specs, contact details or a table from it. Use `firecrawl_search` when additional web sources are needed; on an authenticated session, `firecrawl_map` lists a site's URLs and `firecrawl_crawl` collects a set of pages. `url` may omit the scheme (`example.com/page`); it is read as https. Firecrawl may serve recently indexed content; set `maxAge: 0` for a live fetch or a smaller `maxAge` to bound staleness. A successful response does not by itself confirm the page is still current. A named browser profile loads saved session data without saving changes to it. Authenticated responses can include a `metadata.scrapeId` for optional scrape feedback. On an authenticated session, `firecrawl_search` and `firecrawl_find_tools` can discover providers for the same fields across several pages; a matching provider returns typed records in one call. With `alexandria` in place of `url`, the tool runs catalogued provider capabilities instead of fetching a page. Some providers require accepted terms; when a response reports a terms requirement, direct the user to the Firecrawl dashboard URL in that response.
firecrawl_usage_dashboardOpen the Firecrawl sidebar to browse Alexandria providers, attach tool context to a conversation, and view account credits and monthly usage.Reads text others writeNo findings
Why it is in this group
- The description's first verb is "open": a word for a change.
What it can reach
- untrusted-inputThe description's first sentence says "browse": it reads web pages, which anyone can write.
Description, as the server wrote it Open the Firecrawl sidebar to browse Alexandria providers, attach tool context to a conversation, and view account credits and monthly usage. Requires a connected Firecrawl account. Use firecrawl_credit_usage for data-only reporting.
people_company_enrichUse this first when the user names a person (a name with a company or domain, a LinkedIn URL or an email) or a company and wants contact details, a profile or firmographics, such a…No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it Use this first when the user names a person (a name with a company or domain, a LinkedIn URL or an email) or a company and wants contact details, a profile or firmographics, such as the email of a founder at a given company. One call runs the provider waterfall. Use it, not people_company_search, whenever you have a name with a company or domain, a LinkedIn URL or an email. Give people (name with company or domain, LinkedIn URL, email or phone) or companies (domain, name or LinkedIn URL), up to 10 records per call. Each requested field runs a waterfall by default: Firecrawl tries the providers that can use your inputs one at a time, ordered by listed price, and stops as soon as the field is found. Without contact_fields a person gets a profile and a company gets firmographics; with contact_fields (work_email, personal_email, mobile) each person gets those values and, unless profile is false, the profile in the same call. Ask for mobile only when the task needs a phone number; it is the costliest field and nothing is spent on it otherwise. A work email is on the company domain when one is known and never on a known free-mail domain or a known role mailbox; fields says for each answer which provider gave it, whether the email was verified and whether its domain matched. Set verified_only to get only verified emails. Each result is the provider's raw response, tagged with the provider. A provider that finds the value is charged its listed price; misses are free. max_credits caps the call; without it the call is uncapped. To call one specific provider, use alexandria_library_read instead. Example: {"contact_fields":["work_email"],"people":[{"name":"Jane Doe","domain":"example.com"}]}.
Only reads 21Show 21 read-only tools
firecrawl_agent_activityRead the live progress of a firecrawl_agent job for the Firecrawl agent view: its steps, searches, pages read and credits so far, and the result once it finishes.No findings
Why it is in this group
- The description's first verb is "read": a word for reading.
Description, as the server wrote it Read the live progress of a firecrawl_agent job for the Firecrawl agent view: its steps, searches, pages read and credits so far, and the result once it finishes. Used by the agent view; use firecrawl_agent_status to read a job.
firecrawl_agent_statusRetrieve progress or final results for a `firecrawl_agent` job ID.No findings
Why it is in this group
- The name "firecrawl_agent_status" says "status": a word for reading.
Description, as the server wrote it 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`; a typical research run takes one to three minutes and complex jobs can take longer. If the job cannot finish within the task's available time, use `firecrawl_search` and `firecrawl_scrape` to complete the requested output. Returns job status, progress information, and result data when completed.
firecrawl_check_crawl_statusRetrieve the current status, progress, and available results for an existing crawl ID.Reads text others writeNo findings
Why it is in this group
- The name "firecrawl_check_crawl_status" says "status": a word for reading.
What it can reach
- untrusted-inputThe name "firecrawl_check_crawl_status" says "crawl": it reads web pages, which anyone can write.
- untrusted-inputThe description's first sentence says "crawl": it reads web pages, which anyone can write.
Description, as the server wrote it 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.
firecrawl_credit_usageGet the authenticated Firecrawl team's current credit balance or its credit usage over the last 90 days.No findings
Why it is in this group
- The description's first verb is "get": a word for reading.
Description, as the server wrote it Get the authenticated Firecrawl team's current credit balance or its credit usage over the last 90 days. Use the current view to answer how many credits remain or to check billing-period boundaries. Use the historical view to answer what credits were spent on and when. The current view returns `remainingCredits`, `planCredits`, `billingPeriodStart`, and `billingPeriodEnd`. Extra purchased or granted credits can make `remainingCredits` greater than `planCredits`. Billing-period dates may be null when the upstream billing provider has no period metadata. The historical view returns periods sorted by start date with `startDate`, `endDate`, and `creditsUsed`, one per calendar month, or one per UTC day with `bin: "day"`. Set `byEndpoint` to split each period by the endpoint that used the credits (`endpoint`: scrape, search, crawl, map, agent, ...), or `byApiKey` to split it by API key (`apiKey`). The endpoint split also counts search usage, which the unsplit and per-key figures leave out, so its rows can add up to more. The newest period's `endDate` can be null. A `notice` means the requested split or daily periods are not available yet and the periods are monthly figures. This tool cannot attribute credits to individual jobs, URLs, or MCP clients. Each tool's own result reports what that call used (`creditsUsed`, or `metadata.creditsUsed` on scrapes), and the Usage and Logs pages of the Firecrawl dashboard list usage per job.
firecrawl_developer_searchSearch an index of public repositories, GitHub issues, merged pull requests, repository READMEs, and code documentation for programming questions that need external documentation o…Reads private dataReads text others writeNo findings
Why it is in this group
- The name "firecrawl_developer_search" says "search": a word for reading.
What it can reach
- private-dataThe description's first sentence says "search" and "repository": it reads repositories.
- untrusted-inputThe description's first sentence says "search" and "issue": it reads issues, which other people can write.
Description, as the server wrote it Search an index of public repositories, GitHub issues, merged pull requests, repository READMEs, and code documentation for programming questions that need external documentation or upstream evidence. Returns ranked results with an ID, source type, URL, title, and the matched passages in markdown.
firecrawl_find_toolsBrowse Alexandria data providers and workflows or read a selected contract.Reads text others writeCan send data outNo findings
Why it is in this group
- The name "firecrawl_find_tools" says "find": a word for reading.
What it can reach
- untrusted-inputThe description's first sentence says "browse": it reads web pages, which anyone can write.
- untrusted-inputThe input takes a URL (input.urls), and the tool reads it: it reads web pages, which anyone can write.
- outboundThe input takes a URL (input.urls): a request to a URL can carry data to whoever runs it.
Claude Code: ask, because it is tagged outbound.
Description, as the server wrote it Browse Alexandria data providers and workflows or read a selected contract. Alexandria covers companies, people, jobs, finance and filings, public records and government spending, real estate, places and restaurants, retail and prices, package registries and developer data, news, research, and more: typed, sourced records through published contracts. Use this tool when the contract you need was not returned in full, to browse a category when search found nothing, or before scraping the same fields from several pages. Discovery is free. Use query for semantic discovery or urls to find providers for a website. With no arguments, browse categories, then providers and tools. Contracts describe the inputs and outputs for execution through firecrawl_scrape. nextTool identifies further discovery or pagination. Discovery does not execute providers. Use firecrawl_search when you also need web results.
firecrawl_gov_searchSearch US federal, state, and local statutes, regulations, codes, court opinions, and other government publications for legal or regulatory questions that need primary text.No findings
Why it is in this group
- The name "firecrawl_gov_search" says "search": a word for reading.
Description, as the server wrote it Search US federal, state, and local statutes, regulations, codes, court opinions, and other government publications for legal or regulatory questions that need primary text. Clarify a missing jurisdiction or ambiguous as-of date before identifying the governing rule. Optional filters narrow results by jurisdiction, court, court type, cited law or case, and site. Filters keep only pages the index has labeled, so a filtered search can leave out relevant pages, and no results does not mean none exist. Court labels are most complete for federal courts and case-law collections. Returns ranked results with a position, title, URL, and matched snippet. Results may include historical versions, bill text, agency guidance, and third-party reproductions. Verify the issuer, jurisdiction, enacted/effective status, and version before citing current governing law. Read a known URL or additional page context with firecrawl_scrape. Use general search for non-US questions or missing coverage; no hits does not establish that no applicable law exists.
firecrawl_monitor_checkRetrieve one monitor check and its page-level results, optionally filtered by page status.No findings
Why it is in this group
- The description's first verb is "retrieve": a word for reading.
Description, as the server wrote it 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 of results plus a `next` URL when more pages exist.
firecrawl_monitor_checksList historical checks for a monitor, optionally filtered by status and bounded by a result limit.No findings
Why it is in this group
- The description's first verb is "list": a word for reading.
Description, as the server wrote it 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.
firecrawl_monitor_getRetrieve one monitor by ID, including its configuration and current state.No findings
Why it is in this group
- The name "firecrawl_monitor_get" says "get": a word for reading.
Description, as the server wrote it Retrieve one monitor by ID, including its configuration and current state. This does not run or modify the monitor.
firecrawl_monitor_listList monitors for the authenticated account with optional pagination controls.No findings
Why it is in this group
- The name "firecrawl_monitor_list" says "list": a word for reading.
Description, as the server wrote it List monitors for the authenticated account with optional pagination controls. Returns one page of monitor records and pagination metadata.
firecrawl_provider_directoryList every Alexandria data provider, or every provider in one category, in a single call; with limit, only the first providers in catalogue order.Reads private dataNo findings
Why it is in this group
- The description's first verb is "list": a word for reading.
What it can reach
- private-dataThe name "firecrawl_provider_directory" says "directory": it reads files.
Description, as the server wrote it List every Alexandria data provider, or every provider in one category, in a single call; with limit, only the first providers in catalogue order. Used by the Firecrawl sidebar; free, and it executes no provider. Use alexandria_library_search to browse the catalogue or read contracts (/library/<category>/<provider>/<capability>.md).
firecrawl_recommended_providersList data providers recommended for the connected team from its own Firecrawl activity in the last 30 days, each with the reason it was picked.No findings
Why it is in this group
- The description's first verb is "list": a word for reading.
Description, as the server wrote it List data providers recommended for the connected team from its own Firecrawl activity in the last 30 days, each with the reason it was picked. Used by the Firecrawl sidebar; free, and it executes no provider.
firecrawl_research_inspect_paperRetrieve canonical metadata for one paper ID, such as an arXiv, PMC, PMID, or DOI identifier.No findings
Why it is in this group
- The name "firecrawl_research_inspect_paper" says "inspect": a word for reading.
Description, as the server wrote it 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.
firecrawl_research_read_paperRetrieve in-body passages from one paper that are relevant to a specific question.No findings
Why it is in this group
- The name "firecrawl_research_read_paper" says "read": a word for reading.
Description, as the server wrote it 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.
firecrawl_research_search_papersSearch paper metadata and abstracts with a natural-language query across the indexed corpus, which spans biomedical, life-science, and clinical literature (PubMed, bioRxiv, medRxiv…No findings
Why it is in this group
- The name "firecrawl_research_search_papers" says "search": a word for reading.
Description, as the server wrote it 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, date, and sort options constrain or reorder results. Several distinct framings of the same question surface different papers than a single query does. Returns ranked papers with canonical IDs, titles, authors, and abstracts.
firecrawl_searchUse this when you need current or specific information from the web: recent events, latest releases and versions, prices, people and companies, statistics, or any fact that may hav…Reads text others writeNo findings
Why it is in this group
- The name "firecrawl_search" says "search": a word for reading.
What it can reach
- untrusted-inputThe description's first sentence says "web": it reads web pages, which anyone can write.
Description, as the server wrote it Use this when you need current or specific information from the web: recent events, latest releases and versions, prices, people and companies, statistics, or any fact that may have changed since your training data or that you are not sure of. Returns ranked results with query-relevant highlights; each web result is a title, URL, and description. 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 result types to `research`, `pdf`, `developer`, or `gov`. For a programming question, add `categories: ["developer"]`. It searches an index of public repositories, GitHub issues, merged pull requests, repository READMEs, and code documentation, and returns the results in `data.web` with `category: "developer"`. For a legal or regulatory question, `categories: ["gov"]` returns results in `data.web` with `category: "gov"` and cannot be combined with other categories; authenticated sessions also have `firecrawl_gov_search` as the dedicated tool. Verify gov results' issuer, jurisdiction, status, and version before citing current law. Authenticated search combines web results, semantic tool summaries and domain matches. Use sources: ["alexandria"] for semantic tools only. Authenticated searches always add alexandria to the sources, so sources: ["web"] also returns providers; domainTools: false turns off website-matched tools only. On an authenticated session, tool matches describe available structured-data capabilities, not executed data. toolDetail: "compact" (default) returns only provider, capability and description; "summary" adds metadata; "full" includes their input and output contracts. alexandria_library_read runs a selected capability; alexandria_library_search explores the whole library and reads full contracts. Returns result groups in `data` and an operation `id`.
firecrawl_search_feedbackRecords schema-validated quality feedback for a prior `firecrawl_search` UUID `searchId`.No findings
Why it is in this group
- The name "firecrawl_search_feedback" says "search": a word for reading.
Description, as the server wrote it Records schema-validated quality feedback for a prior `firecrawl_search` UUID `searchId`. A `good` rating requires a valuable result or a valuable source, `partial` either of those or at least one `missingContent` entry, and `bad` at least one `missingContent` entry or a query suggestion; caps are 50 `valuableResults`, 50 `valuableSources`, and 20 `missingContent` entries. Eligibility is limited to successful searches within the feedback age window. The record is idempotent per search ID. Eligible first feedback for a search can refund 1 credit; refunds are subject to the team's daily cap. The response reports whether a refund was applied, along with submission and daily-cap status. Mark useful returned results in `valuableResults` as `{"source", "position"}` copied off the result. Groups are numbered from 1 independently, so `{"source":"web","position":1}` and `{"source":"news","position":1}` are different results. Be exhaustive — results you do not list are treated as not useful. Reserve `valuableSources` for useful URLs that were NOT among the returned results; never report one result in both fields.
jobs_searchFind job postings and check whether a posting is still open.Reads text others writeCan send data outNo findings
Why it is in this group
- The name "jobs_search" says "search": a word for reading.
What it can reach
- untrusted-inputThe input takes a URL (input.url), and the tool reads it: it reads web pages, which anyone can write.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Claude Code: ask, because it is tagged outbound.
Description, as the server wrote it Find job postings and check whether a posting is still open. Use it to: find jobs by role and place (query, with location, remote or posted_within_days); read one posting by url and tell whether it is still open; check up to 10 posting urls in one call; list a company's open roles from its own job board (company, a name or domain; add query for one role there); and see who is hiring for a role (query with group_by "employer"). Every row has the same normalized fields: title, company, location, remote, posted_at as the board states it, url, source, a status, and checked_at, the time Firecrawl read it. status is open when the posting was read from the employer's board or live posting page in this call, and unverified when it comes from a job site and was not confirmed on the employer's board. A posting checked by url can also be closed, not_found or error. A single url returns the full description; list rows carry it with include_description. A company search names the boards it read and what each covers; when no board is found, rows come from job sites and notes says so. boards_only searches employers' own boards only. Each provider read is charged its listed price; max_credits caps the call. Example: {"query":"data engineer","location":"Berlin","posted_within_days":14}.
people_company_searchFind people or companies you don't know yet, by filters.No findings
Why it is in this group
- The name "people_company_search" says "search": a word for reading.
Description, as the server wrote it Find people or companies you don't know yet, by filters. Not for someone you can already name: for a named person (with their company or domain, a LinkedIn URL or an email) or a named company, call people_company_enrich instead; a request naming one person is refused and pointed there. Set entity to "person" or "company" and give filters: people by title, seniority, function, employer and location; companies by industry, headcount, location, technology, keywords or founding year. Firecrawl asks its search providers one at a time, cheapest first, and only those that apply every filter given. When none does, it searches companies first and then people at those companies; a request no provider or chain covers is refused naming the filter to drop. With company_domains the search stops at the first provider that finds anyone; otherwise it fills limit across up to three providers. Rows carry name, title, company, location and LinkedIn URL, never emails or phones: use people_company_enrich for contact details. Each provider call is charged its listed price; max_credits caps the call. Example: {"entity":"person","filters":{"titles":["Head of Data"],"company_domains":["example.com"]},"limit":10}.
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Exfil surface
Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.
198 paths in this server alone from private data, through text someone else wrote, to a way out. Denying 2 private-data tools breaks every one.
- Reads private data2
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write11
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out9
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
{
"permissions": {
"deny": [
"mcp__firecrawl__firecrawl_developer_search",
"mcp__firecrawl__firecrawl_provider_directory"
]
}
}Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.
Remote posture
What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.
Looked at Nov 17, 2026, 15:25 UTC, unchanged since Nov 17, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 200
- tools/list served without credentials
- yes
- Tools that change things, listed without credentials
- 17
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- https://nova.civai.co/.well-known/oauth-protected-resource/mcp/agents/mcp-firecrawl
- Authorization servers
- https://nova.civai.co
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- yes
- Client ID metadata documents
- yes
- HighThe whole server
The endpoint served tools/list without credentials, and the list has 17 tools that change things (1 destructive, 16 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://nova.civai.co/mcp/agents/mcp-firecrawl: tools/list returned 38 tools to an anonymous client, including firecrawl_monitor_delete (destructive), firecrawl_scrape (write), firecrawl_map (write), alexandria_library_search (write), alexandria_library_read (write) and 12 more
Posture changes
- Nov 17, 2026
- Tools that change things, listed without credentials: 14 to 17
- Nov 10, 2026
- Tools that change things, listed without credentials: 13 to 14
Findings
Matches of fixed checks, with the text they matched.
The description mentions "credentials".
What this check looks forMatched text
description: "...s the end user's own browser cookies or credentials. By default it starts with no cookies o..."
History
Changes to its tool definitions and to its remote endpoint, newest first.
PostureRemote posture changed. Tools that change things, listed without credentials: 14 -> 17.View diff
- Tools that change things, listed without credentials: 14 to 17
Tools6 added, 13 changed.+6 added~13 changedView diff
- Added:alexandria_library_readChanges things
- Added:alexandria_library_searchChanges things
- Added:firecrawl_agent_activityOnly reads
- Added:jobs_searchOnly reads
- Added:people_company_enrichChanges things
- Added:people_company_searchOnly reads
- Changed:firecrawl_agentChanges thingsdescriptioninputSchema
- Changed:firecrawl_crawlChanges thingsdescriptioninputSchema
- Changed:firecrawl_feedbackChanges thingsdescriptioninputSchema
- Changed:firecrawl_find_toolsOnly readsdescriptioninputSchema
- Changed:firecrawl_interactChanges thingsdescriptioninputSchema
- Changed:firecrawl_mapChanges thingsdescriptioninputSchema
- Changed:firecrawl_monitor_createChanges thingsinputSchema
- Changed:firecrawl_monitor_updateChanges thingsdescriptioninputSchema
- Changed:firecrawl_parseChanges thingsinputSchema
- Changed:firecrawl_provider_directoryOnly readsdescriptioninputSchema
- Changed:firecrawl_research_search_papersOnly readsdescriptioninputSchema
- Changed:firecrawl_scrapeChanges thingsdescriptioninputSchema
- Changed:firecrawl_searchOnly readsdescriptioninputSchema
PostureRemote posture changed. Tools that change things, listed without credentials: 13 -> 14.View diff
- Tools that change things, listed without credentials: 13 to 14
Install
Pinned to version 1.0.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http firecrawl https://nova.civai.co/mcp/agents/mcp-firecrawlclaude mcp add --transport http firecrawl https://nova.civai.co/mcp/agents/mcp-firecrawlRun in a terminal.
Claude Code permissions
Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [
"mcp__firecrawl__firecrawl_search",
"mcp__firecrawl__firecrawl_search_feedback",
"mcp__firecrawl__firecrawl_check_crawl_status",
"mcp__firecrawl__firecrawl_agent_status",
"mcp__firecrawl__firecrawl_monitor_list",
"mcp__firecrawl__firecrawl_monitor_get",
"mcp__firecrawl__firecrawl_monitor_checks",
"mcp__firecrawl__firecrawl_monitor_check",
"mcp__firecrawl__firecrawl_research_search_papers",
"mcp__firecrawl__firecrawl_research_inspect_paper",
"mcp__firecrawl__firecrawl_research_related_papers",
"mcp__firecrawl__firecrawl_research_read_paper",
"mcp__firecrawl__firecrawl_developer_search",
"mcp__firecrawl__firecrawl_gov_search",
"mcp__firecrawl__people_company_search",
"mcp__firecrawl__firecrawl_credit_usage",
"mcp__firecrawl__firecrawl_recommended_providers",
"mcp__firecrawl__firecrawl_provider_directory",
"mcp__firecrawl__firecrawl_agent_activity"
],
"ask": [
"mcp__firecrawl__firecrawl_scrape",
"mcp__firecrawl__firecrawl_map",
"mcp__firecrawl__firecrawl_find_tools",
"mcp__firecrawl__alexandria_library_search",
"mcp__firecrawl__alexandria_library_read",
"mcp__firecrawl__firecrawl_feedback",
"mcp__firecrawl__firecrawl_crawl",
"mcp__firecrawl__firecrawl_agent",
"mcp__firecrawl__firecrawl_interact",
"mcp__firecrawl__firecrawl_interact_stop",
"mcp__firecrawl__firecrawl_parse",
"mcp__firecrawl__firecrawl_monitor_create",
"mcp__firecrawl__firecrawl_monitor_update",
"mcp__firecrawl__firecrawl_monitor_run",
"mcp__firecrawl__people_company_enrich",
"mcp__firecrawl__jobs_search",
"mcp__firecrawl__firecrawl_usage_dashboard"
],
"deny": [
"mcp__firecrawl__firecrawl_monitor_delete"
]
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as firecrawl. Review it before you use it.
Capability tags behind 15 rules
- mcp__firecrawl__firecrawl_scrape untrusted-input, outbound
- mcp__firecrawl__firecrawl_map outbound
- mcp__firecrawl__firecrawl_search untrusted-input
- mcp__firecrawl__firecrawl_find_tools untrusted-input, outbound
- mcp__firecrawl__firecrawl_feedback untrusted-input, outbound
- mcp__firecrawl__firecrawl_crawl untrusted-input, outbound
- mcp__firecrawl__firecrawl_check_crawl_status untrusted-input
- mcp__firecrawl__firecrawl_agent outbound
- mcp__firecrawl__firecrawl_interact outbound
- mcp__firecrawl__firecrawl_interact_stop untrusted-input
- mcp__firecrawl__firecrawl_monitor_create untrusted-input, outbound
- mcp__firecrawl__firecrawl_developer_search private-data, untrusted-input
- mcp__firecrawl__jobs_search untrusted-input, outbound
- mcp__firecrawl__firecrawl_usage_dashboard untrusted-input
- mcp__firecrawl__firecrawl_provider_directory private-data
Pin
Keep the decision: fail CI when the tools change, follow every change, or show a badge.
Pin in CI
Fail a build when the tools you reviewed are not the tools the server serves today.
curl -s "https://radar.anlyon.com/api/v1/servers/co.civai.nova/mcp-firecrawl/verify?hash=ac52d52dc0ff74ab40f996c1aa5d34ae21d2f048cb6a5a33197121d1f0bf6d27" | jq -e '.changed == false'Pinned hash ac52d52dc0ff, from Nov 15, 2026, 14:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/co.civai.nova/mcp-firecrawl/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/co.civai.nova/mcp-firecrawl)Source: MCP Registry. Synced Nov 2, 2026, 09:17 UTC.
Firecrawl by Nova (CIVAI) MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Firecrawl by Nova (CIVAI) MCP server safe?
- No scan can promise that. What its definitions show: 37 tools, 16 of which can change, send or delete something, and 1 finding from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the Firecrawl by Nova (CIVAI) MCP server delete data?
- Yes. 1 tool can delete, cancel or revoke something: firecrawl_monitor_delete.
Can the Firecrawl by Nova (CIVAI) MCP server do things that cannot be undone?
- No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.
What tools does the Firecrawl by Nova (CIVAI) MCP server have?
- 37 tools: 1 destructive, 15 write, 21 read. firecrawl_monitor_delete, firecrawl_scrape, firecrawl_map, alexandria_library_search, alexandria_library_read, firecrawl_feedback, firecrawl_crawl, firecrawl_agent and 29 more.
Does the Firecrawl by Nova (CIVAI) MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the Firecrawl by Nova (CIVAI) MCP server send data to outside services?
- 9 tools can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): firecrawl_scrape, firecrawl_map, firecrawl_find_tools, firecrawl_feedback, firecrawl_crawl, firecrawl_agent and 3 more.
Has the Firecrawl by Nova (CIVAI) MCP server changed its tools?
- Yes, once since Anlyon Radar started tracking it, most recently on Nov 15, 2026. Every change is on this page and in its Atom feed.