Skip to main content
Glama
spidra-mcp-server

spidra-mcp-server

Official
by spidra-io

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
HOSTNoHTTP transport bind host (default localhost)
PORTNoHTTP transport bind port (default 3000)
SPIDRA_API_KEYYesYour Spidra API key (spd_...)
SPIDRA_API_URLNoOverride the API base URL (self-hosted / staging)
HTTP_STREAMABLE_SERVERNotrue to serve HTTP streamable transport at http://localhost:3000/mcp instead of stdio

Instructions

Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.

This server publishes no instructions, or was last inspected before Glama recorded them.

Capabilities

Features and capabilities supported by this server

Protocol revision2025-11-25

CapabilityDetails
tools
{
  "listChanged": true
}
logging
{}
completions
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
spidra_searchA

Search the web and get back ranked results: titles, links and descriptions, as a search engine shows them. Waits and returns the results, usually in a few seconds.

Use it when you don't know the URL yet, want news, images or videos, or want research papers (arXiv, PubMed, bioRxiv, medRxiv) or GitHub issues and pull requests. Don't use it for a URL you already have: spidra_scrape reads it directly and can extract fields with a prompt or schema.

  • Only "web" results come back unless you set "sources". Each source runs on its own, and an empty one doesn't affect the others. "research" and "developer" ignore includeDomains, excludeDomains and filetype.

  • "includeDomains" or "excludeDomains" (never both) keeps results to, or away from, certain sites.

  • More results: send a source's token from "nextPageTokens" back as "pageTokens" (e.g. {"web": ""}). Ranks continue (11, 12, ...). A source with no token has no more pages.

  • "scrapeOptions" also returns each web result's page as Markdown in the same call. It then takes as long as the slowest page and costs a scrape per page. Results from popular sites (Amazon, LinkedIn, YouTube and others) also get "structuredData".

  • Don't add the current year to queries unless the user asked for it; it skews results.

Cost: 1 credit per 10 results per source, rounded up. A source with no results is free.

Example: {"query": "best espresso machine", "sources": ["web", "news"], "limit": 5}

spidra_mapA

List a website's page URLs without scraping them, from its sitemaps and the links on its pages. Waits and returns the URLs, usually in a few seconds.

Use it when you need the right pages on a site before reading them ("which page on stripe.com covers refunds?"), or a full list of a site's URLs. Then: pick the URLs you need and read exactly those with spidra_scrape or spidra_batch_scrape. That's usually cheaper than spidra_crawl when you only need a few pages.

  • "search" keeps only matching URLs, best matches first. Keep "limit" small when you only need a few.

  • "total" is how many URLs matched; "scanned" is how many were found in all.

Cost: 1 credit per call. Free when no URLs are found.

Example: {"url": "https://docs.python.org/3/", "search": "asyncio", "limit": 20}

spidra_scrapeA

Read one known URL and get its content as Markdown, or the data you describe as JSON. Waits and returns the result, usually in a few seconds (up to a minute for hard pages).

Use it for one URL. Links to PDF, Word, Excel and PowerPoint files work too. Don't use it for more than one URL, even to compare two: spidra_batch_scrape gives each URL its own result. To find pages on a site, use spidra_map or spidra_crawl.

  • No "prompt" or "schema": the page as Markdown.

  • "prompt": what you want, in plain words; the AI picks the shape. Add "schema" for exact fields and types (null where the page has nothing).

  • Popular sites (Amazon, Google Maps, LinkedIn, YouTube, Zillow, Indeed and others): with "output": "json" and no prompt, "content" is the page's data in named fields, no AI needed. Otherwise that data is in "structuredData".

  • "actions" runs browser steps first (click, type, scroll, forEach to go through a list); "instruction" does one task described in plain words instead. Never both. Steps run once and are never retried automatically, since a step like a form submission has effects.

  • If the result has "lowContent": true, the page came back nearly empty, usually because the site blocks automated visits. Call again with "useProxy": true.

Cost: 1 credit, plus AI credits for the tokens used with a prompt or schema (often 1 or 2), plus 5 per CAPTCHA solved. A page that can't be read costs nothing.

Browser actions: up to 50 steps (click, type, check, uncheck, hover, select, press, wait, waitFor, scroll, scrollUntilEnd, evaluate, screenshot, forEach), with waits adding up to 60 seconds at most. "selector" is CSS, XPath, or plain words ("the Sign in button"); prefer CSS when you know it. A failed step fails the job (free) with "Action N (...) failed: "; mark steps that may not be there, like cookie banners, "optional": true. forEach goes through a list of items and must be the single, last action. "actionResults" reports each step as ok, skipped or failed.

Example: {"url": "https://books.toscrape.com", "prompt": "Return the title and price of every book", "output": "json"} Example with actions: {"url": "https://quotes.toscrape.com/login", "actions": [{"type": "type", "selector": "#username", "value": "demo"}, {"type": "type", "selector": "#password", "value": "demo"}, {"type": "click", "selector": "input[type='submit']"}, {"type": "waitFor", "selector": "a[href='/logout']"}], "prompt": "List the first 3 quotes with their authors", "output": "json"}

spidra_batch_scrapeA

Read 2 to 50 known URLs, each on its own with its own result, using the same prompt or schema for all.

Use it for anything with more than one URL: product pages, listings, articles, or just two pages to compare. Waiting: with "wait": true and 10 URLs or fewer, it waits (up to a few minutes) and returns the finished batch. Otherwise it returns a "batchId" straight away; check it with spidra_get_job (type "batch") every 10 to 15 seconds until "status" is completed or cancelled. Don't start the batch again while it runs.

  • "output" is "markdown" (default) or "json"; a schema sets "json". Popular-site pages also get "structuredData".

  • A completed batch can still have failed items: check "failedCount" and each item's "error". spidra_retry_batch re-runs only the failed ones.

  • Browser actions aren't supported in a batch; use spidra_scrape for pages that need them.

Cost: per URL, the same as spidra_scrape. Failed URLs cost nothing.

Example: {"urls": ["https://books.toscrape.com/catalogue/a-light-in-the-attic_1000/index.html", "https://books.toscrape.com/catalogue/tipping-the-velvet_999/index.html"], "prompt": "Title and price", "output": "json", "wait": true}

spidra_crawlA

Start at one URL and follow links to the kind of pages you describe, optionally extracting data from each. Returns a "jobId" straight away.

Use it when you need many pages of one kind and don't know their URLs (every blog post, every product in a category, every page of docs). Don't use it when you know the URLs (spidra_batch_scrape) or only need a site's list of URLs (spidra_map, much cheaper). Then: check it with spidra_get_job (type "crawl") every 10 to 15 seconds until it's completed, failed or cancelled. Don't start it again while it runs. Stop a mistake with spidra_cancel_job.

  • "crawlInstruction" says which pages to return, e.g. "Individual book pages" or "Blog posts, not tag pages".

  • "transformInstruction" or "schema" extracts data from each page with AI. Leave both out for each page as Markdown, with no AI cost.

  • "maxPages" counts only pages returned (default 5). Pages read just to find them are free. Plan limits per crawl: Free 100, Starter 1,000, Builder 5,000, Pro 10,000.

  • The crawl stays under the start URL's path unless "crawlEntireDomain" is true.

  • A page you expected is missing? spidra_crawl_report says why each link was skipped.

Cost: 1 credit per page returned, plus AI credits with a transformInstruction or schema. A crawl that returns nothing is free.

Example: {"baseUrl": "https://books.toscrape.com", "crawlInstruction": "Individual book pages", "transformInstruction": "Title and price", "maxPages": 10}

spidra_crawl_pagesA

Read a crawl's pages, in order, with each page's data and links to its Markdown and HTML (the links last 1 hour). Use it for crawls of more than 100 pages, since spidra_get_job returns only the first 100, or after a cancelled crawl to get the pages it finished.

Page through with "offset" and "limit" until "hasMore" is false. Keep "limit" small (20 to 50) to save context. Each page's "id" is what spidra_retry_crawl_page needs.

spidra_crawl_reportA

Explain a finished crawl: how it read the instruction, how many pages it read only to find the wanted ones (free), and every link it didn't follow, counted by reason. Pass "reason" to list the URLs for one reason, each with the page it was found on.

Use it when a page you expected is missing, then adjust crawlInstruction, includePaths or maxPages and crawl again. Reasons: not_relevant, outside_domain, include_pattern, exclude_pattern, file_type, other_version_or_language, duplicate_page, redirected_off_site, robots_txt, action_link. The report is empty while the crawl runs.

spidra_crawl_extractA

Run a new extraction over every page a finished crawl saved, without visiting the site again. Much cheaper than crawling again: only AI credits are charged. Returns a new "jobId"; check it with spidra_get_job (type "crawl"). The original crawl doesn't change.

spidra_retry_crawl_pageA

Run a crawl's extraction again on one saved page and return the new data. It doesn't visit the site, and the page's stored data is replaced. Use it when one or two pages came back empty or wrong. Get "pageId" from spidra_crawl_pages (each page's "id"). Only crawls with a transformInstruction or schema can be retried. Costs only the AI credits for that page.

spidra_parseA

Turn documents into Markdown, page by page, and into JSON with a "prompt" or "schema". PDF, Word, Excel, PowerPoint, OpenDocument, RTF, EPUB, CSV and HTML files work, and scanned pages are read with AI.

Use it for reports, papers, invoices, contracts and spreadsheets, online or given to you as a file. Don't use it for web pages (spidra_scrape).

Send the documents one way:

  • "url": a link to one document.

  • "fileBase64" and "fileName": a file you have, base64-encoded (up to about 10 MB).

  • "fileId": a document parsed in the last 24 hours, to parse again with other options.

  • "urls" or "fileIds": several documents at once (up to 50), each parsed with the same options.

  • "pages" ("1-5, 9" or "10-") or "maxPages" parses only part of a long PDF.

  • "dryRun": true returns the page count and cost, for free, without parsing.

  • It waits up to about 50 seconds. A long document or a batch still running returns an id; check it with spidra_get_job (type "parse" or "parse_batch").

Cost: 1 credit per page parsed, plus AI credits with a prompt or schema. Formats without pages count one page per 3,000 characters. Failed pages and documents cost nothing.

Example: {"url": "https://arxiv.org/pdf/1706.03762", "pages": "1-3"}

spidra_find_templatesA

Find ready-made templates: jobs that turn a few inputs into a table of results, such as Google Maps leads with emails, Amazon keyword rank, LinkedIn or Indeed jobs, YouTube transcripts, Zillow homes or Google Flights prices. Free.

Use it first when the task is a common data job on a well-known site. A template is usually cheaper and more complete than writing scrapes yourself. Then: spidra_get_template for its inputs, and spidra_run_template to run it.

Filter with "q" (words, e.g. "reviews"), "site" (e.g. "google-maps", "amazon") or "category". With no filter you get every template; the response also lists the site keys and categories to filter by.

spidra_get_templateA

Get what a template needs and what it returns: its inputs (send them by "key" to spidra_run_template; "required" ones must be set, others have defaults), its columns, and its limits in plain words. Free.

spidra_run_templateA

Run a template and get its rows. Most runs finish in this call (it waits up to about 45 seconds). A longer one returns a "runId"; check it with spidra_get_job (type "template_run") every 10 to 15 seconds until "status" isn't "running".

  • Get the inputs from spidra_get_template first. Send them in "inputs" by key.

  • "estimate": true checks the inputs and returns the credits it should cost, for free, without running.

  • Rows come back with the template's columns. "detail": "full" returns every field. Rows page with "offset" and "limit" (default 50).

  • A "partial" run had some pages fail; its rows are still there, with the failures listed.

Cost: what the same job costs with the tool behind it, usually 1 credit per page read. Failed pages and failed runs cost nothing.

Example: {"slug": "google-maps-leads", "inputs": {"query": "dentist", "areas": ["Lekki, Lagos"]}}

spidra_list_presetsA

List the user's saved presets, newest first: saved template runs (a template and its inputs) and saved tool requests. Pass "presetId" to get one in full. Run one with spidra_run_preset.

spidra_save_presetA

Save a job so it can run again with one call, or change a saved one.

  • A template preset: "kind": "template", the template's "template" slug and its "inputs".

  • A tool preset: "kind": "tool", the "tool" (scrape, batch, crawl, map, search or parse) and "config", the request body exactly as that tool takes it. Cookies are never stored.

  • To change one, pass its "presetId" and only the fields that change ("name", "description", "inputs" or "config").

Presets can also be watched for changes with spidra_create_monitor.

spidra_run_presetA

Run a saved preset. "overrides" changes template inputs, or request fields of a tool preset, for this run only.

A template preset returns its template run (check a running one with spidra_get_job, type "template_run"). A tool preset returns that tool's own answer: map links straight away, or a scrape, batch, crawl or search job id to check with spidra_get_job. Costs what the same job costs when run directly.

spidra_delete_presetA

Delete a saved preset. Runs already made from it stay in the history. A monitor that watches it starts failing until its sources are changed. Confirm with the user before deleting.

spidra_create_monitorA

Watch a template, a preset or a list of pages on a schedule and get an alert when something changes: new or removed items, changed fields (like a price), or page text changes.

  • The first check runs straight away and records the starting point without alerting.

  • "estimate": true returns the credits per check and per month, for free, without creating it.

  • "testNotification": true sends a sample alert to the "notify" channels, without creating anything, to check a webhook, Slack or Discord URL.

  • The plan limits how many monitors the user can have and how often they check (spidra_account shows it).

  • Confirm the schedule and channels with the user before creating, since each check costs credits.

Cost: each check costs what running its sources costs. A "goal" adds a little AI on checks where something changed.

Example: {"name": "Cable price", "sources": [{"kind": "urls", "urls": ["https://www.amazon.com/dp/B0CG1LGWR6"]}], "schedule": {"every": "1d", "at": "09:00", "timezone": "Africa/Lagos"}, "alertOn": "changed", "watchFields": ["price"], "goal": "Only tell me if the price drops"}

spidra_list_monitorsA

List the user's monitors with their schedule, last check and next check. Pass "monitorId" to get one in full. What changed is in spidra_monitor_changes.

spidra_update_monitorA

Change a monitor, or pause and resume it. Send only what changes; the fields are the same as spidra_create_monitor. "status": "paused" stops checks and keeps the history; "active" starts them again. Changing "sources" restarts the comparison for new sources, and "notify" replaces all channels.

spidra_delete_monitorA

Delete a monitor and its check history. To stop checks but keep the history, pause it with spidra_update_monitor instead. Confirm with the user before deleting.

spidra_check_monitorA

Run a monitor's check now, outside its schedule. It runs in the background, costs what a scheduled check costs, and alerts like one. Once a minute at most per monitor. Read the result with spidra_monitor_changes after a little while.

spidra_monitor_changesA

A monitor's checks, newest first, with a one-line summary of each. Pass "checkId" for everything one check found, per source: new, changed and removed items (with old and new values), and page text changes. A source's first check has "baseline": true and only records the starting point. Checks are kept for 30 days.

spidra_get_jobA

Get any job's status, and its result once finished. Use it for the ids other tools return when they don't wait to the end.

  • "scrape", "search": a jobId. Readable for about an hour after it finishes (failed ones 24 hours); after that, use spidra_logs.

  • "batch": a batchId. A completed batch can still have failed items; check "failedCount".

  • "crawl": a jobId. Returns the first 100 pages; spidra_crawl_pages reads the rest.

  • "parse": a jobId. "includePages" adds each page's Markdown.

  • "parse_batch": a batchId.

  • "template_run": a runId. Rows come back with the template's columns ("detail": "full" for every field) and page with "offset" and "limit".

Check every 10 to 15 seconds while it runs. Statuses: queued, waiting, active and running are still in progress; completed, partial, failed and cancelled are final.

spidra_cancel_jobA

Cancel a running batch, crawl or search.

  • "batch": URLs not yet started are stopped and their held credits returned; finished ones keep their results. A cancelled batch can't be retried.

  • "crawl": stops at its next check. If it had returned pages, it ends completed with those (charged as usual); if not, cancelled and free. spidra_crawl_pages still reads its pages.

  • "search": one not yet started is removed; a running one stops at its next checkpoint and then reports failed with "Search cancelled".

spidra_retry_batchA

Run a batch's failed URLs again with the batch's original options; the rest are left alone. Use it after spidra_get_job shows "failedCount" above 0. Cookies are never stored, so pass "cookies" again if the batch used them. Then check the batch with spidra_get_job as before. A URL that fails again costs nothing.

spidra_accountA

The user's plan, credits left this billing period, Stealth Mode bandwidth, and how many monitors the plan allows. Use it before a large batch, crawl or template run to check there's enough, or to answer "how many credits do I have".

  • "usage" adds credits, requests and tokens per day ("7d", "30d") or per week ("weekly").

  • "byTool": true adds credits per day split by tool (scrape, crawl, search, parse, map) for the last 7 days, or the "usage" range.

"credits.used" includes credits held by jobs still running; unused held credits come back when they finish.

spidra_logsA

Find past runs, newest first, or open one by its id. Every run is logged, including ones made in the dashboard, and logs last after the job itself can no longer be read with spidra_get_job.

  • "tool": scrape, search, map, parse, crawl, batch or template.

  • "id": open one log in full, with its result. For scrape, search and map this is the log's "uuid" (not the job's id); for crawl and template it's the job's id. A parse log's "jobId" opens with spidra_get_job (type "parse"), and a batch with spidra_get_job (type "batch").

  • "status" and "searchTerm" filter scrape, search, map and parse logs. Scrape: success, error, in_progress. Search: also cancelled. Map: success, empty, error. Parse: queued, running, completed, failed.

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

TDQS

A4.1/5.0

Scored across 28 tools

Disambiguation4/5

Core scraping, search, map, parse, template, and monitor tools have explicit use/don't-use guidance, so major choices are clear. Some boundaries remain around job/result retrieval (spidra_get_job vs spidra_crawl_pages vs spidra_logs) and retry tools, requiring description reading.

Naming Consistency3/5

All tools use the spidra_ prefix, which helps grouping. However patterns mix bare verbs (spidra_scrape, spidra_search, spidra_map), verb_noun (spidra_get_job, spidra_create_monitor), noun_verb (spidra_batch_scrape), and noun-only names (spidra_account, spidra_logs).

Tool Count3/5

28 tools is heavy for an MCP surface and exceeds the typical 3-15 range. The categories are coherent and many tools are justified by the platform's breadth, but the set is still at the borderline-to-too-many end.

Completeness4/5

The surface covers single/batch scraping, crawling, URL mapping, search, document parsing, templates, presets, monitors, job control, account, and logs. Lifecycle coverage is strong; only minor gaps like consolidated job listing or broader job management remain.

Maintenance

ActivityNo data
ResponsivenessOutdated data