Firecrawl MCP Server vs Warp Agent MCP
A side-by-side look at the Firecrawl MCP Server and Warp Agent MCP MCP servers: transport, auth, tools, quality signals, and the config to install either one in Claude, Cursor, Windsurf or VS Code.
Verdict: choose Firecrawl MCP Server for search & data extraction work as a local process; choose Warp Agent MCP for delivery as a local process. You can also run both side by side in one mcpServers block.
Which MCP server should you choose?
Choose Firecrawl MCP Server when
- You need dedicated capabilities in the Search & Data Extraction domain.
- You prefer a local stdio subprocess transport.
- Its auth model fits you: API key required.
- You have the keys it needs:
FIRECRAWL_API_KEY, HTTP_STREAMABLE_SERVER, FIRECRAWL_NO_SEARCH_FEEDBACK, FIRECRAWL_NO_ENDPOINT_FEEDBACK. - You want tools like
firecrawl_scrape, firecrawl_map, firecrawl_search.
Choose Warp Agent MCP when
- You need dedicated capabilities in the Delivery domain.
- You prefer a local stdio subprocess transport.
- Its auth model fits you: API key required.
- You have the keys it needs:
WARP_API_KEY, WARP_API_URL. - You want tools like
freight_workflow, compare_freight_costs, van_quote.
Feature & specification comparison
Rows where the two servers differ are marked.
| Spec | ||
|---|---|---|
| Category | Search & Data Extraction | Delivery |
| Quality signal | 90/100 · Excellent | 65/100 · Great |
| Install command | Confirmed | Confirmed |
| Transport | Local subprocess (stdio) | Local subprocess (stdio) |
| Auth | API key required | API key required |
| Pricing | Freemium | Paid service |
| Required env vars | FIRECRAWL_API_KEYHTTP_STREAMABLE_SERVERFIRECRAWL_NO_SEARCH_FEEDBACKFIRECRAWL_NO_ENDPOINT_FEEDBACK | WARP_API_KEYWARP_API_URL |
| Verified owner | Verified | Community listing |
| GitHub stars | 7,642 | 5 |
| Directory activity | 13 views 0 installs 0 upvotes | 3 views 0 installs 0 upvotes |
| Tools | 25 | 33 |
| Full listing | View Firecrawl MCP Server | View Warp Agent MCP |
Tools & capabilities
Firecrawl MCP Server tools 25
firecrawl_scrapeRetrieve 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 operates on a known page. For a set of pages use `firecrawl_crawl`, and to discover page URLs use `firecrawl_map` or `firecrawl_search`. Options include JavaScript render delay, cache age, main-content filtering, PII redaction, and lockdown cache-only retrieval. Browser actions may change the live page when interactive actions are enabled. Firecrawl may reuse recently indexed content instead of refetching the page, and the reuse window varies by domain. Set `maxAge: 0` to force a live fetch, or a smaller `maxAge` to bound how stale reused content may be. A successful response does not by itself confirm that the state it describes is still current. Returns the selected content formats and page metadata.firecrawl_mapEnumerate 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 rather than page bodies. Retrieve one page with `firecrawl_scrape`; collect content across multiple pages with `firecrawl_crawl`.firecrawl_searchSearch 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: ["developer"]`. It searches an index of GitHub issues, merged pull requests, repository READMEs, and curated documentation sites, and returns the hits in `data.developer` beside the web results. `categories: ["research"]` restricts these web results to research-affiliated websites and returns page snippets. The `firecrawl_research_*` tools are a separate surface that searches paper abstracts and full text across biomedical (PubMed, bioRxiv, medRxiv) and arXiv literature. `scrapeOptions` can attach extracted page content; pages fetched this way use a fixed reuse window and ignore `maxAge`, so use `firecrawl_scrape` when a live fetch is required. Returns source-type result groups and usage metadata. Authenticated responses can include an `id` for optional search feedback.firecrawl_crawlStart 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. Returns the crawl ID, status, and page data.firecrawl_check_crawl_statusRetrieve 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_extractDeprecated 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.firecrawl_agentStart 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 it reaches `completed` or `failed`; research commonly takes several minutes. If the job cannot finish within the task's available time, `firecrawl_search` and `firecrawl_scrape` can gather evidence synchronously.firecrawl_agent_statusRetrieve 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 requested output. Returns job status, progress information, and result data when completed.firecrawl_interactOpen 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, stdout/stderr, exit status, and session viewing URLs.firecrawl_interact_stopStop the live interact session associated with a `scrapeId` and release its resources. Returns a success confirmation.firecrawl_parseParse 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.firecrawl_monitor_createCreate 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.- +13 more on the listing page
Warp Agent MCP tools 33
freight_workflowGet a ready-to-use shipment intake CSV header, results CSV header, and starter prompt for shipment quoting, weekly freight comparison, or invoice review. Guidance only: does not read files, fetch rates, schedule work, or book. Use this when an operator asks how to start or supplies invoices/a shipment sheet.compare_freight_costsCalculate USD cost differences for up to 50 distinct shipments using supplied invoice/quote amounts and explicit comparability evidence. Excludes mismatched or unknown terms, keeps losses, separates quoted opportunities from invoice differences. Does not fetch rates, verify documents, annualize savings, or book. One candidate per shipment per call.van_quoteQuote a cargo van shipment (1-3 pallets, firm price)box_truck_quoteQuote a 26' box truck shipment (1-12 pallets, firm price)ftl_quoteQuote a full truckload (53' dry van). Only origin, destination, and date required.ltl_quoteQuote an LTL shipment — returns Warp's all-inclusive rate FAST (~1-2s) so the user sees a price immediately. The inline quote card shows the Warp rate plus a 'finding other carrier rates…' loading indicator. IMMEDIATELY follow up by calling ltl_market_options with the same parameters to fill in the multi-carrier comparison (~15s). Provide dims + commodity for an exact firm quote; if you don't have dims, quote anyway — it assumes a standard 48x40x48 pallet (FAK, no freight class) for an instant price. Don't block on asking for pallet dimensions; quote first, then pass real dims for an exact rate. When a palletized load could also move by box truck or van, quote LTL alongside those and show the cheapest valid mode. Do not editorialize the results. Do not declare a winner or recommend a specific carrier. Present Warp's quote first, then list market options as context. Let the user decide.ltl_market_optionsMulti-carrier LTL comparison — returns 30+ carrier rates ranked by price (slow, ~15s). Call IMMEDIATELY AFTER ltl_quote with the same parameters; this fills in the 'finding other carrier rates…' section the fast quote card was showing. Useful when the user wants to compare carriers or pick a specific one. Do not declare a winner or recommend a specific carrier; just present the ranked list.compare_modesTHE ONE CALL for "what's the cheapest/best way to ship this?". Prices ALL FOUR freight modes (LTL / full truckload / cargo van / 26' box truck) in ONE keyless call to Warp's all-modes engine and returns a decision-complete recommendation: the winning mode, its rate, transit, a bookable quote_id, the trade-off math against the runner-up, and every mode that couldn't price (with the reason). Prefer this over calling the individual quote tools and comparing them yourself — one round trip, and modes Warp can't serve are returned as explicitly unavailable WITH the reason rather than being dropped, so there is never a silently shortened list to guess from. Dims are optional (a standard 48x40x48 pallet is assumed). Set benchmark_market:true to also rank Warp's rate against the live 30+ carrier market for the lane (adds ~15-25s) — that makes the answer decision-complete: the right mode AND whether the price is actually good. Quote-only: it never books. To book, pass the recommended quote_id to `book` after the user confirms.batch_quotePrice up to 50 lanes in one call for a specified mode per row (defaults to LTL). This returns a Warp rate per row, NOT all-mode or all-carrier comparison. For Compare All use compare_modes per shipment; for LTL carrier alternatives use ltl_market_options. Never imply this tool compared every carrier. Returns a single batch-quote card with one row per lane (origin → dest · mode · pallets · price · transit). Each priced lane keeps its quote_id and can be booked individually with book ("book row 3").bookBook a quoted shipment using any quote_id or option id returned from a quote tool (Warp or market carrier). Requires quote_id + pickup and delivery addresses. Auth required.batch_bookBook MANY already-quoted lanes in ONE call (sequential, one card charge per row). Use this after batch_quote when the user says "book all of them" or "book rows 1, 3, 5" — do NOT call book in a loop. Each row needs a quote_id (the same one batch_quote returned for that row). Pickup/delivery default to the shared addresses at the top level so a single warehouse → many destinations only needs one address pair. Returns a progress card showing per-row Booked/Failed status with tracking numbers.multistop_quoteQuote a multi-stop FTL route: ONE truck visits 3+ stops in order (first pickup → intermediate stops → final delivery). Use for milk runs, pool distribution, or multi-store replenishment on a single truck — for a simple A→B truckload use ftl_quote. Auth required (free account). Coverage is route-dependent — not every route has a rate yet.- +21 more on the listing page
Ready-to-paste client configs
Paste either block (or both) into your client config, e.g. claude_desktop_config.json or ~/.cursor/mcp.json. We only show a config when the install command is confirmed.
Firecrawl MCP Server
{
"mcpServers": {
"firecrawl-firecrawl-mcp-server": {
"command": "npx",
"args": [
"-y",
"firecrawl-mcp"
],
"env": {
"FIRECRAWL_API_KEY": "YOUR_FIRECRAWL_API_KEY_HERE",
"HTTP_STREAMABLE_SERVER": "YOUR_HTTP_STREAMABLE_SERVER_HERE",
"FIRECRAWL_NO_SEARCH_FEEDBACK": "YOUR_FIRECRAWL_NO_SEARCH_FEEDBACK_HERE",
"FIRECRAWL_NO_ENDPOINT_FEEDBACK": "YOUR_FIRECRAWL_NO_ENDPOINT_FEEDBACK_HERE"
}
}
}
}
Warp Agent MCP
{
"mcpServers": {
"warpfreight-warp-agent-mcp": {
"command": "npx",
"args": [
"-y",
"warp-agent-mcp"
],
"env": {
"WARP_API_KEY": "YOUR_WARP_API_KEY_HERE",
"WARP_API_URL": "YOUR_WARP_API_URL_HERE"
}
}
}
}
Frequently asked questions
Firecrawl MCP Server is categorized under Search & Data Extraction and uses a local stdio subprocess. Warp Agent MCP belongs to Delivery and uses a local stdio subprocess. Pick Firecrawl MCP Server for search & data extraction work and Warp Agent MCP for delivery.
Copy the mcpServers block from the config section on this page into your client's config (for example claude_desktop_config.json or ~/.cursor/mcp.json), then fully restart the client.
Firecrawl MCP Server is listed as freemium — a free tier with paid plans. Auth: api key required. Warp Agent MCP is listed as a paid service. Auth: api key required. If a server needs environment variables such as API keys, define them under the env key in your client's MCP config.
Yes. MCP clients support multiple servers: add firecrawl-firecrawl-mcp-server and warpfreight-warp-agent-mcp as separate keys in the same mcpServers object, and your assistant will call tools from either one.
On AllMCPs, Firecrawl MCP Server has a quality signal of 90/100 (Excellent) with 13 views, 0 installs and 7,642 GitHub stars. Warp Agent MCP has 65/100 (Great) with 3 views, 0 installs and 5 GitHub stars.