"MCP servers that support SSE connections" matching MCP connectors:
GET /v1/connectors – MCP directory API referenceMatching Connector Tools:
teas.co.uk is an independent UK online tea shop. Its MCP server gives AI assistants four tools. ask_lee: Ask Lee, the shop's tea adviser, as a chat that remembers the conversation; it understands and answers in 10 languages, keeps to a budget with delivery included, gives a price per cup for tea bags and loose leaf, and says plainly when an ingredient cannot be ruled out. teas: the shop as a small website inside the chat, with search and filters, full tea pages (pictures, taste scores, brewing timer), compare, brands, offers, the Tea Wiki (about 1,500 articles), recipes, news and Under the Hood. basket: add, change and undo, a quote with UK or international delivery, and a secure checkout link; a repeated request is never added twice, and the customer always pays on teas.co.uk. my_account: after the customer links their teas.co.uk account (OAuth), orders, tracking, invoices, reward points, repeat deliveries and returns. About 400 teas, herbal and fruit infusions and hot chocolates from 40 brands. No sign-in is needed to shop. Endpoint https://teas.co.uk/mcp, with a backup address at https://teas.co.uk/wp-json/teas/v1/shop-mcp.
Review accounting data and available financial records within your authorized workspace. This listing retains the complete 18-tool Accounting service and its existing full endpoint. For new tasks, start with Samuelz® Accounting · Evidence checks. Choose from Evidence checks, Individual reminder, Cost allocation, Existing reminder run at https://platform.samuelz.com/integrations?lang=en#accounting. Each task view is a subset, not a replacement for the full service. Existing URLs and conversations keep working. Changing views grants no additional rights and does not migrate a running conversation. Prepared operations keep their identity and approval requirements; read their status before any recovery. Setup: In a remote MCP client that supports Streamable HTTP and OAuth, add https://platform.samuelz.com/api/v1/mcp/operator?toolset=accounting. Sign in to Samuelz and select your authorized workspace. Active workspace membership and the relevant module permissions are required. Review requested permissions before authorizing. Existing human approvals and separate cost permissions continue to apply.
Vira is an AI behavior infrastructure that lets learn, manage, and apply reusable behaviors across AI systems. Through MCP, agents can discover tasks, teach new behaviors from evidence, create and manage Behavior Packs, run evaluations, control releases, and verify behavior at runtime. Bring consistent, versioned, and traceable behavior to your AI without relying on scattered prompts or repeated model training. Built for agent-first workflows, with support for scoped execution, verification, and continuous improvement.
Skavio LLC hosts 20 OAuth-protected Streamable HTTP tools for PDF, searchable OCR, invoice/receipt fields, audio and document workflows. Paid jobs debit company-scoped prepaid Skavio credits (1 USD = 1,000 credits), with quotes, max_credits caps and idempotent settlement. Only the company administrator can fund its wallet. Linked Agent Tools companies can buy Stripe card packs of USD 5-500 or use USDC at https://getskavio.com/agent-tools/dashboard.html. Processing OAuth and Agent Tools credentials are separate; never assume automatic wallet sharing. Four independent blockchain proof/DNS tools still require x402 native USDC. MCP endpoint: https://getskavio.com/processing/mcp ; Docs: https://getskavio.com/processing/docs/mcp/ ; Support: support@getskavio.com. No paid external card-to-MCP job E2E verified yet.
Work with website content and available Sites tasks in your connected workspace. Setup: In a remote MCP client that supports Streamable HTTP and OAuth, add https://platform.samuelz.com/api/v1/mcp/operator?toolset=website. Sign in to Samuelz and select your authorized workspace. An active workspace membership and Website/Sites module permissions are required. Review the requested permissions before authorizing. Existing approval requirements continue to apply.
Manage contacts, organizations and their recorded relationships in your workspace. Setup: In a remote MCP client that supports Streamable HTTP and OAuth, add https://platform.samuelz.com/api/v1/mcp/operator?toolset=crm. Sign in to Samuelz and select your authorized workspace. An active workspace membership and the relevant module permissions are required. Review the requested permissions before authorizing. Existing approval requirements continue to apply.
CRM1Prepare and follow podcast, episode and editorial work in your connected Media OS. Setup: In a remote MCP client that supports Streamable HTTP and OAuth, add https://platform.samuelz.com/api/v1/mcp/operator?toolset=media. Sign in to Samuelz and select your authorized workspace. An active workspace membership and the relevant module permissions are required. Review the requested permissions before authorizing. Existing approval requirements continue to apply.
Customer feedback analysis over MCP. Your agent creates a survey, gets the fill link or embed snippet, adds feedback you already have (reviews, support e-mails, exported rows) and reads insights with the exact quotes they were counted from. Each quote carries its responseId and position, so the agent can check it with list_responses. Under ten complete responses, get_insights returns not-enough-data with the count and the threshold. No tool deletes anything or submits a response. OAuth or an API key. Basic and Pro plans, also in the 14-day trial.
Delegate to an AI agent that runs your small business, or script the Crevio API and 3,000+ apps.
The form builder that ends the back-and-forth
Work with roles, tasks and delegated agent work within current workspace permissions. Setup: In a remote MCP client that supports Streamable HTTP and OAuth, add https://platform.samuelz.com/api/v1/mcp/operator?toolset=agent. Sign in to Samuelz and select your authorized workspace. An active workspace membership and the relevant module permissions are required. Review the requested permissions before authorizing. Existing approval requirements continue to apply.
Review recorded business policies and their current approval boundaries. Setup: In a remote MCP client that supports Streamable HTTP and OAuth, add https://platform.samuelz.com/api/v1/mcp/operator?toolset=policy. Sign in to Samuelz and select your authorized workspace. An active workspace membership and the relevant module permissions are required. Review the requested permissions before authorizing. Existing approval requirements continue to apply.
Shared Markdown memory that every AI assistant can read and write. Hosted in the EU.
Arsen is a human risk management platform that enables security teams to assess employee exposure through advanced phishing, voice phishing, and deepfake simulations, and strengthen their resilience with adaptive cybersecurity awareness training. Arsen MCP connects your Arsen platform to your preferred AI assistant, including Claude, ChatGPT, and any MCP-compatible assistant. With Arsen MCP, you can: 1. Build and launch campaigns. Let your AI assistant prepare phishing simulation campaigns and cybersecurity awareness programs, then launch them with your approval. 2. Get actionable insights from your data. Ask questions in plain language and get answers based on your organization's actual data, including campaign results, click, compromise and reporting rates, phishing score trends, coverage, and teams that need attention. 3. Manage multiple client organizations. Give MSSPs the ability to query and work across every client organization they manage, from a single AI assistant. Secure by design. Users authenticate with their Arsen account (SSO and MFA supported), and every request is governed by their existing Arsen permissions.
Work with personal goals, measurements, reviews and next actions in Results OS. Setup: In a remote MCP client that supports Streamable HTTP and OAuth, add https://platform.samuelz.com/api/v1/mcp/results. Sign in to Samuelz and select your authorized workspace. An active workspace membership and the relevant module permissions are required. Review the requested permissions before authorizing. Existing approval requirements continue to apply.
Work with books, sources, series and publication jobs through the existing publishing workflow. Setup: In a remote MCP client that supports Streamable HTTP and OAuth, add https://platform.samuelz.com/api/v1/mcp/operator?toolset=books. Sign in to Samuelz and select your authorized workspace. An active workspace membership and the relevant module permissions are required. Review the requested permissions before authorizing. Existing approval requirements continue to apply.
The integration hub for your CRM, field service and accounting apps. One plugin, two separate parts: integrations between two of your systems, and AI agents inside one of them. It connects the CRM, field service, accounting and online store systems small businesses run on. Don't see your system? Request it, right in the chat. Part 1. Integrations between two systems Set up in the chat, then they keep two of your systems in sync by themselves, so a new customer, a won deal or a paid invoice shows up where your team works without copying it by hand. - See which systems connect and what two systems can sync, no account needed - Choose the records that travel, one way or both ways, and the moment they travel: when paid, won, accepted or overdue - Ready rules, such as a won deal that becomes a draft invoice - Which fields go across, and how each system connects - Set it up in the chat, or get a link that opens the setup prefilled - For CRM Connector customers: your integrations, what failed and why, sync now, pause or resume Part 2. AI Agents inside one system An AI agent works with the records of one of your systems. Request your system right in the chat: we arrange the setup and enable it for your account, then you sign in to it. - AI Analyst: it reads your customer data, such as contacts, deals and invoices, and finds the same customer in your other connected systems - AI Agent: it also changes records when you ask, each change shown first, risky ones approved by you in CRM Connector - Automations: fixed rules inside that one system (when this happens, only if, then do that), made in the chat, approved once by you in CRM Connector, then run by the platform by itself - A change log with undo where the system allows it - Nothing in AI Agents syncs between two systems: that is an integration You stay in control: - You choose per system and per record type what the assistant may see or change - Changing records is a separate permission on the consent page, off unless you allow it - An automation never runs before you approve it, and you can pause or remove it at any time - It never deletes a record and never records a payment - It sets up, runs or pauses an integration only when you ask and confirm, and never deletes one - Disconnect at any time in CRM Connector under Settings, AI Assistants
A living map of all your work that keeps you, your team, and your agents on the same page
The last mile of AI adoption: an agent that ships real work, with your brand and your rules.
Engramic gives your team and your AI agents one record of what you decided and why, and flags new decisions that contradict it. It's built on three ideas: Memory, Context and Consistency.
MSG91 is a cloud communication platform that helps businesses improve customer engagement, streamline communication workflows, and increase operational efficiency through reliable, multi-channel communication solutions.
Ask about your own Meta (Facebook and Instagram) ad account right in Claude, ChatGPT or Cursor. Run1Ads checks your ads, Pixel and store every hour and tells you the one fix that matters today, ranked by buyers lost, with exact steps. It advises only and never changes your ads. Free for a limited time.
tri-train is a training platform for triathletes that syncs activities from Strava and Garmin and exposes them to Claude through a remote MCP server. Ask Claude how your last block went, why your run pace dropped, or whether you are fresh enough for Sunday's race, and it answers from your real data: activities with laps and grade-adjusted pace, weekly load and the performance management chart (CTL/ATL/TSB), sleep, HRV and resting heart rate, and your race calendar with predictions. Claude can also act: create and adjust planned workouts with structured intervals, push them to your Garmin watch, add races and write notes. Every change is journaled and can be undone. Read and write access are separate OAuth scopes, and the server enforces them on every call. Built and hosted in Switzerland by a triathlete; data stays on our own servers (Swiss revDSG / GDPR).
Toolstile is a managed MCP gateway that connects remote MCP servers behind one endpoint, with per-agent permissions, shared accounts and activity logs. Connect at https://mcp.toolstile.com/mcp over Streamable HTTP with OAuth; sign in at https://toolstile.com, select a workspace and connect your upstream servers. Available tools, resources and prompts depend on that workspace and the agent's granted access.
Turn a customer request into a complete HPE server configuration that loads straight into HPE's OCA configurator, without leaving Claude or ChatGPT. For HPE partners in Europe and the UK. Sign up at https://www.oyster.tech/join/connector for free credits; setup guide at https://www.oyster.tech/connectors.
RedirX turns a site's old and new URL lists into a redirect map, working through the AI agent you already use. Connect the remote MCP server and sign in with OAuth. Your agent imports the two URL inventories, and RedirX proposes a destination for each old URL. Every proposal stays in review until you confirm it: confirm the clear matches, settle the ambiguous ones, and RedirX uses your confirmed examples to revisit what is still unresolved. Only approved mappings are exported, as Apache, Nginx, WordPress Redirection, Vercel, Cloudflare Pages, Shopify, CSV or JSON. Once the redirects are installed, verify_redirects checks the live site over HTTP. Nothing is published to your site automatically. RedirX produces the redirect file; you decide what ships. Works with Claude Code, Claude Desktop, Codex, Cursor and VS Code. Agents without an MCP client can follow the skill file at redirx.dev/skill.md. Pricing: the first migration is free for up to 500 old URLs, no card required. After that, $0.02 per old URL ($10 minimum), or monthly plans at $79 (5,000 old URLs) and $199 (15,000).
AgentiSend is a transactional email API: send through verified domains with a message log, budgets, a preflight and refusals that name the fix; built so AI agents can send on your behalf. The hosted MCP server at https://api.agentisend.com/mcp exposes 82 tools (44 on tools/list; the rest via list_more_tools). A send is one message or a batch of up to 500 items with per-item results. preflight_email runs every gate a real send runs, sends nothing, and costs nothing. Every 4xx returns code, message, and fix. There is no tool for unsolicited mail. Auth is a bearer API key or OAuth 2.1 with dynamic client registration. Starter prompts: "Send this receipt to the customer." "Preflight this send and tell me what would stop it." "What can I spend today?"
SEO that executes: keywords, calendar, articles written, scored and published to your CMS, backlinks
AI search visibility MCP: brand mentions in ChatGPT and Perplexity, Google AI Overview citations. Whether ChatGPT and Perplexity mention a brand for a buyer's question and which sources they cite, and which pages Google's AI Overview cites for a keyword. Use to check brand mentions and cited sources for specific ChatGPT or Perplexity prompts, or Google AI Overview citations for a keyword. This focused SEO Data subset provides sampled checks, not continuous monitoring or an overall visibility score. Billing: paid data calls use API credits; get_api_credit_balance is free. The focused connections and SEO Data use the same balance and prices. Example prompts: - Check whether ChatGPT mentions my brand for the buyer question I provide, after I approve the API-credit spend. - Within my approved API-credit budget, check Perplexity brand mentions and cited sources for my prompt. - After confirming the API-credit cost, show Google's AI Overview sources for my keyword and report when no overview is returned. Docs: https://docs.crakseo.com/mcp-servers/ai-visibility
Anry is a read-only MCP server that ties every ad click to the visit and the order, puts a price on where an online store loses money, and gives the fix to the store's own AI agent.
The five-star chef calorie tracker: meals that fill you up, logged in one sentence.
Video review and collaboration for teams and agents: a full review interface for agentic video and motion graphics, feedback by voice, screen and drawing on the frame, agents that iterate version by version, and every version's notes and source files saved for the team.
Google rank checker MCP: live positions, ranked keywords, competitor domains and keyword gaps. Check a domain's live Google positions for up to 10 keywords per call, retrieve ranked keywords, find organic competitors and compare competitor keyword gaps. Results are snapshots, not built-in scheduled tracking or ranking history. Use to check current Google positions or research competitor keywords. This is a focused SEO Data subset. Use Search Console instead for your own connected site's historical performance; this connection does not schedule future checks. Billing: paid data calls use API credits; get_api_credit_balance is free. The focused connections and SEO Data use the same balance and prices. Example prompts: - Check my domain's live Google positions for these five keywords in the US after I approve the per-keyword API-credit spend. - Within my approved API-credit budget, show keywords the supplied domain currently ranks for. - Find competitor domains and keyword gaps for my domain after confirming the API-credit cost. Do not imply this sets up scheduled tracking. Docs: https://docs.crakseo.com/mcp-servers/rank-tracker
Teable is an AI spreadsheet for business that combines a familiar spreadsheet interface with a structured database. Its remote MCP server lets AI agents inspect project and table structure, read and update records, and access the Teable API through OAuth with existing project permissions. Website: [teable.ai](https://teable.ai)
Local SEO MCP: Google Maps rankings, Google Business Profile ratings and review counts. Google Maps positions for a keyword in a city with rating, review count, category and address, and a business's Google Business Profile with rating distribution and claimed status. Use for point-in-time Google Maps rankings and Google Business Profile lookup by location. This focused SEO Data subset returns rating and review-count summaries, not full review text, review replies or Business Profile management. Billing: paid data calls use API credits; get_api_credit_balance is free. The focused connections and SEO Data use the same balance and prices. Example prompts: - Check Google Maps results for 'running shoe store' in the city I specify after I approve the API-credit cost. - Within my approved API-credit budget, compare Maps rankings for the same keyword in two specified places. - After confirming the API-credit spend, retrieve the business profile I specify and summarize its rating and review counts, not review text. Docs: https://docs.crakseo.com/mcp-servers/local-seo
SEO site audit MCP: up to 5 supplied URLs for on-page issues, plus Lighthouse page-speed scores. On-page and technical SEO checks for up to 5 pages (status code, on-page score, title, meta description, H1, canonical, word count, links, load time and every failed check), plus Lighthouse scores and Core Web Vitals for a page. Use before publishing or after a migration to check up to 5 supplied URLs per audit, or inspect a page's speed. This is a focused SEO Data subset, not an automatic whole-site crawler. Distinguish Lighthouse lab checks from field measurements. Billing: paid data calls use API credits; get_api_credit_balance is free. The focused connections and SEO Data use the same balance and prices. Example prompts: - Audit the owned page I provide for title, headings and canonical issues after I approve the API-credit spend. - Within my approved API-credit budget, compare failed technical checks for up to five supplied pages. - After confirming the API-credit cost, report Lighthouse scores and available Core Web Vitals for my page, distinguishing lab checks from field data. Docs: https://docs.crakseo.com/mcp-servers/site-audit
Backlink checker MCP: backlink summary, top backlinks, referring domains and anchor texts. A backlink summary (rank, backlinks, referring domains, broken links, spam score) and the strongest backlinks with anchor text and follow status, plus referring domains and anchor text counts for any domain or URL. Use to analyze backlinks, referring domains and anchor text for your site or a competitor. This focused SEO Data subset checks links; it does not submit backlinks for indexing. For a backlink indexer, use the separate URL Indexing server's paid Force indexing offering. Billing: paid data calls use API credits; get_api_credit_balance is free. The focused connections and SEO Data use the same balance and prices. Example prompts: - Check my domain's backlink summary and top backlinks after I approve the API-credit spend. - Within my approved API-credit budget, list the referring domains for the domain I provide. - After confirming the API-credit cost, summarize the anchor texts in my domain's link profile without assuming they prove a penalty. Docs: https://docs.crakseo.com/mcp-servers/backlinks
Keyword research MCP: search volume, CPC, keyword difficulty and keyword ideas by country. Monthly search volume, CPC, competition, keyword difficulty and intent for any keyword and country, keyword ideas from seed terms, and the keywords a competitor ranks for that you don't. Use for keyword ideas, search volume, CPC, difficulty and competitor keyword gaps when planning content or choosing targets. This is a focused subset of SEO Data; connect it instead of the toolkit when you only need keyword research. Billing: paid data calls use API credits; get_api_credit_balance is free. The focused connections and SEO Data use the same balance and prices. Example prompts: - Compare search volume and CPC for my keyword batch in the US after I approve the API-credit cost. - After confirming the API-credit spend, compare keyword difficulty for my shortlist and explain the limits of the estimates. - Find keyword ideas and competitor keyword gaps for the seed and domains I provide, within my approved API-credit budget. Docs: https://docs.crakseo.com/mcp-servers/keyword-research
# **RChilli** RChilli MCP Hub is a production-grade Model Context Protocol (MCP) server that exposes RChilli’s HR data intelligence platform through AI-callable tools. Built on 15+ years of HR data intelligence, RChilli supports ATS vendors, HR technology platforms, staffing agencies, and enterprise recruiting teams worldwide. The tools return consistent, structured JSON responses for recruiting, talent intelligence, skills, matching, compliance, and HR workflow use cases. `userkey` and `subuserid` are injected automatically from the Bearer token and must not be passed manually. <br> --- <br> # **Available Tools** <br> > ### **`analyze_hr_call`** > > Transcribes and analyzes HR or recruiting call recordings to extract speaker turns, sentiment, candidate intent, action items, skill mentions, and structured follow-up data for recruiting operations. <br> > ### **`analyze_skill_adjacency`** > > Identifies related, adjacent, and transferable skills to support skill discovery, talent mobility, workforce planning, and candidate evaluation. <br> > ### **`analyze_skill_gap`** > > Compares candidate or employee skills against a target job and returns present skills, missing skills, readiness score, and development areas for hiring, internal mobility, and workforce planning. <br> > ### **`autocomplete_job_profile`** > > Accepts a partial job title and returns ranked autocomplete suggestions with canonical titles and job families. Ensures job titles map to standardized taxonomy profiles from the moment a recruiter starts typing. <br> > ### **`autocomplete_skill`** > > Accepts a partial skill string and returns ranked autocomplete suggestions with canonical skill names and categories. Helps prevent free-text entry errors and keeps skill data clean. <br> > ### **`classify_job_zone`** > > Reads the job profile from a resume or job description and returns its O*NET Job Zone, from Zone 1 through Zone 5, based on the education, experience, and training preparation required for the role. <br> > ### **`convert_document_format`** > > Accepts a document as base64 or URL and converts between PDF, DOCX, RTF, HTML, and plain text. Useful as a pre-processing step before extracting data from non-standard document formats. <br> > ### **`detect_bias`** > > Reviews job descriptions and hiring criteria for gendered language, age-coded terms, unnecessary credential inflation, cultural exclusion signals, and related compliance risks. Suggests neutral replacements. <br> > ### **`detect_resume_suspicion`** > > Reviews candidate profile data for possible inconsistencies, unusual claims, timeline conflicts, missing context, and other signals that require recruiter review. <br> > ### **`extract_contacts`** > > Identifies and structures names, emails, phone numbers, LinkedIn URLs, and addresses with field-level confidence scores from candidate records, emails, or documents. <br> > ### **`extract_job_data`** > > Extracts and converts job descriptions into structured hiring data including job title, required skills, preferred skills, responsibilities, experience, education, and taxonomy-normalized role requirements. <br> > ### **`extract_resume_data`** > > Extracts and converts resumes, CVs, and candidate documents into structured, searchable profiles with contact details, skills, experience, education, certifications, and taxonomy-enriched data for ATS, HCM, and AI recruiting workflows. Supports multilingual extraction, batch processing, resume auto-fill, and reprocessing of historical resumes. <br> > ### **`extract_resume_data_from_url`** > > Accepts a direct URL to a PDF, DOCX, or RTF file and returns the same normalized JSON profile as Resume Data Extraction. Ideal for resumes stored in cloud storage, S3, email attachments, or other URL-accessible sources. <br> > ### **`find_matches_in_index`** > > Accepts a resume or job description as input and returns the top matching documents from the indexed corpus, ranked by semantic similarity. <br> > ### **`generate_interview_questions`** > > Creates technical, behavioral, situational, and competency-based interview questions tailored to a role and candidate profile, including question type, competency, and expected answer signals. <br> > ### **`generate_jd`** > > Generates structured job descriptions with title, responsibilities, required skills, preferred skills, qualifications, tone alignment, language support, and inclusivity scoring from role inputs. <br> > ### **`geolocate`** > > Converts partial or informal location text into structured city, state, country, ISO codes, latitude, and longitude. Supports radius-based candidate search and workforce planning. <br> > ### **`index_document`** > > Indexes a resume or job description in RChilli Search & Match so it can be searched, matched, updated, and reused across candidate matching, job matching, and similarity-search workflows. <br> > ### **`lookup_job_profile`** > > Returns authoritative detail for a known job profile including canonical title, SOC/O*NET code, job family, typical required and preferred skills, salary bands, and work context. <br> > ### **`lookup_skill`** > > Returns authoritative detail for a known skill including description, aliases, related skills, proficiency levels, and O*NET or ESCO mappings. <br> > ### **`map_job_to_skills`** > > Converts job descriptions into granular skill maps with required and preferred skill clusters, proficiency signals, taxonomy tags, and downstream matching attributes. <br> > ### **`match_end_to_end`** > > Orchestrates data extraction, indexing, taxonomy normalization, and matching to return ranked candidates or jobs with scores, explainable results, and an audit trail from a single call. <br> > ### **`normalize_candidate_data`** > > Cleans and normalizes candidate records from multiple ATS or HR systems, resolves field conflicts, deduplicates records, and produces standardized candidate data with a field-level change log. <br> > ### **`normalize_hr_data_with_lov`** > > Maps raw and inconsistent HR data values, including degrees, universities, certifications, job profiles, skills, and locations, to the closest configured List of Values entry with a standardized value and confidence score. <br> > ### **`recommend_learning_path`** > > Builds structured learning paths with prerequisites, skill sequence, certifications, proficiency targets, and LMS alignment based on a person’s profile and target role. <br> > ### **`redact_resume`** > > Redacts configured personally identifiable information from candidate profiles to support anonymized review, bias-aware screening, compliance workflows, and audit logs. <br> > ### **`reformat_resume_with_template`** > > Applies one of the RChilli resume templates, TM001 through TM006, to a structured candidate profile and produces a consistently formatted PDF, DOCX, RTF, or HTML document. <br> > ### **`score_resume_against_jd`** > > Accepts one resume and one job description and returns an overall match score, dimension scores, matched skills, skill gaps, and a natural-language explanation. No index is required. <br> > ### **`screen_application_batch`** > > Evaluates a batch of candidates against job requirements and custom criteria, returning scores, insights, skill gaps, and recommended next actions for each candidate. <br> > ### **`search_indexed_documents`** > > Accepts a query string and returns ranked document references from the tenant’s indexed corpus. Supports Boolean and semantic search modes. <br> > ### **`skill_mapping`** > > Maps raw skill text to standardized RChilli taxonomy skills, aliases, classifications, and related skill information. <br> > ### **`tag_entities`** > > Annotates extracted HR text by wrapping recognized entities in structured XML-style labels. Supported entities include job titles, skills, names, degrees, organizations, locations, countries, dates, and years.
Your unified inbox — everything that reaches you, understood and actionable from your AI assistant.
Google SERP API MCP: live Google, Bing, AI Overview and Google Maps results as JSON. Pay per call. Live search engine results pages as structured JSON: Google organic results with SERP features and AI Overview sources, Bing results, Google Maps local results, and live Google rank checks for a domain across up to 10 keywords. Use when an agent needs live Google or Bing search results for a keyword, country, language and device. This is a focused subset of SEO Data, not an additional required connection or a scheduled monitoring service. Billing: paid data calls use API credits; get_api_credit_balance is free. The focused connections and SEO Data use the same balance and prices. Example prompts: - Show the top ten Google results and SERP features for 'trail running shoes' in the US, after I approve the API-credit spend. - Compare Google and Bing results for my keyword in the same market, within my approved API-credit budget. - After confirming the API-credit cost, report which source URLs Google's AI Overview cites for my keyword. If none is present, say so. Docs: https://docs.crakseo.com/mcp-servers/serp-api
SEO data MCP: SERP, keywords, backlinks, live rank checks, page audits, local and AI checks. Every SEO data tool in one server: Google and Bing SERP results, live rank checks, AI Overview sources, keyword search volume, ideas and difficulty, backlinks, referring domains and anchors, ranked keywords, competitor domains and keyword gaps, site audits with Lighthouse scores, Google Maps rankings, Google Business Profiles, and ChatGPT and Perplexity brand mentions. Start here for paid SEO research with one connection. Includes all seven focused SEO data servers' tools at the same prices and from the same API-credit balance; do not connect both for duplicate results. Search Console reporting and URL Indexing are separate connections. Billing: paid data calls use API credits; get_api_credit_balance is free. The focused connections and SEO Data use the same balance and prices. Example prompts: - After I approve the API-credit cost, compare US search volume and difficulty for 'trail running shoes' and 'running shoes for flat feet'. - For the domain I provide, check its backlink summary, referring domains and anchor texts after confirming the API-credit spend. - Compare live Google positions and competitor keyword opportunities for my domain and keywords, within the API-credit budget I approve. Docs: https://docs.crakseo.com/mcp-servers/seo
Stop manually creating generic reports that don't match your gym! Ask your AI about your studio's sales, classes and clients. Mindbody MCP server for Claude and ChatGPT. Connect your studio once, then ask about sales, classes, clients and memberships. Not affiliated with Mindbody.
Google indexer: free IndexNow, Bing, sitemap and index checks; paid backlink force indexing Google indexer and URL indexer for AI agents. Free URL submission for sites you own: IndexNow and Bing Webmaster Tools, sitemap resubmission to Google Search Console, and a free index checker (Search Console URL inspection) that finds pages stuck in 'Crawled - currently not indexed' or 'Discovered - currently not indexed'. Force indexing (paid) is the fast indexing service: a backlink indexer and link indexer that pushes any public URL, including backlinks and pages you don't own, to Google through a third-party indexing service so Googlebot crawls it sooner. It uses URL credits, always shows an exact quote first and needs the account owner's approval; Google still decides what it indexes. It never uses the Google Indexing API. Which one do I need? New page missing from Google: Free URL submission + index check first, then Force indexing if still not indexed. Backlinks or links you don't own: Force indexing. 'Crawled - currently not indexed' or 'Discovered - currently not indexed': free index check, then Force indexing. Is my page indexed?: check_if_url_is_indexed (free). Notify Bing and other IndexNow engines: Free URL submission. Fast or instant indexing searches: Force indexing, without any indexing or timing guarantee. Google has no public indexing API, so free submission can't force Google; Force indexing is the paid option. Free URL submission: IndexNow (Bing, Yandex, Seznam, Naver), Bing Webmaster Tools, sitemap resubmission to Google Search Console, and a free Google index checker through Search Console URL Inspection. For sites you own or have connected. Force indexing (paid): 1 URL credit per URL the third-party indexing service accepts. Always an exact quote first, then account-owner approval in the dashboard. No indexing, ranking or timing guarantee. Tools: - Free: Free URL submission: IndexNow (`submit_urls_to_indexnow`) - Free: Free URL submission: Bing Webmaster Tools (`submit_urls_to_bing`) - Free: Free URL submission: IndexNow, Bing and the Google next step (`notify_search_engines_free`) - Free: Free index check: are URLs indexed in Google (`check_if_url_is_indexed`) - Free: Submit a sitemap to Google and Bing (`submit_sitemap`) - Paid: Force indexing: read URL credits and readiness (`get_force_indexing_balance`) - free to call; no purchase or indexing-service call - Paid: Force indexing: quote URLs (backlink and Google indexer) (`quote_force_indexing`) - Paid: Force indexing: submit approved quote (`submit_force_indexing`) - Paid: Force indexing: read job (`get_force_indexing_job`) - Paid: Force indexing: list jobs (`list_force_indexing_jobs`) Example prompts: - "Is https://example.com/new-post indexed in Google? If not, resubmit my sitemap." - "Index these 5 backlinks in Google: quote Force indexing and wait for my approval." - "My pages show 'Crawled – currently not indexed' in Search Console; check them and suggest a fix." Search keywords and tags (most searched first): google indexer, google indexing, page indexer, website indexer, web indexer, indexnow, submit website to google, index checker, google index checker, submit url to google, link indexer, backlink indexer, index backlinks, seo indexer, crawled currently not indexed, discovered currently not indexed, url indexer, google crawl request, indexing service, link indexing service, rapid indexing, request indexing, instant indexing, fast indexing, force indexing, force crawl google Docs: https://docs.crakseo.com/mcp-servers/url-indexing Free URL submission and Force indexing: https://docs.crakseo.com/seo-mcp/managed-indexing
Connect AI assistants to Snapstay to look up hotel reservations, availability, rates, guests, and performance. OAuth lets hotel teams select one property and approve read or write access. Public beta for independent and boutique hotels. Setup: https://snapstay.ai/support#assistant-help
Inspect saved Thumble controllers, registered phones and delivery receipts. Includes a Mac-to-phone pairing QR handoff. OAuth required (email code, Google or Apple). Six read-only tools; generation, saving and sending are disabled. Use built-in ConsolePort for play. Rendered confirms phone rendering, not Mac input or game bindings. Docs: https://thumble.io/docs | Privacy: https://thumble.io/privacy | Terms: https://thumble.io/terms | Support: cody@isolated.tech
Autonomous AI customer support engine with 81 FastMCP tools, website crawling, WooCommerce sync, calendar booking, and live human takeover.
Create songs from prompts or lyrics, check credits, and access your private song library through an OAuth-connected MCP server. Uses your existing Words into Music account, song credits and limits. Songs support English, Spanish, German, French and Brazilian Portuguese. Documentation: https://wordsintomusic.com/mcp/
Give your AI a network of real people. Marcel is an MCP server that lets your AI find and connect you with people who can help. Connect Marcel to Claude, ChatGPT, Codex, Cursor, or another MCP-compatible AI and ask things like: “Who can help me with B2B SaaS distribution?” “Find someone who has hired a customer success team.” “Do I have any new connection requests?” Marcel uses your profile and network to find relevant people and explain why an introduction makes sense. No social feed. No f
Zyte MCP is a remote MCP server that lets an agent use Zyte on your behalf. It can download pages with a plain HTTP request or in a real browser, click and type and take screenshots, and pull structured data out of a page with AI, either as a standard type like product, article or job posting or as fields you describe in plain words. It can also search the web from a chosen country, check whether Zyte API supports a site and what a request costs, and report your usage by domain. If you have Scrapy Cloud projects, the same server can list spiders, start and cancel jobs, read logs and items, manage schedules and settings, and read and write collections. Those tools can change and delete things, so review what your agent asks to do. Connect to https://mcp.zyte.com/v1/mcp and sign in to your Zyte account with OAuth. Using the server is free. What your agent does through it is billed at Zyte API prices, on a dedicated mcp_access_key you can track and cap. New accounts get $5 of trial credit for a month.
Plot turns the trips you plan with an AI assistant into a real, shared itinerary. Connect it and your assistant can save flights (every leg), hotels, restaurants, activities, trains and car rentals to the right day in local time, read your trips back, and update or delete bookings. Sign in with your Plot account; there are no API keys. Works with ChatGPT, Claude, Muse and any client that supports remote MCP.
fomox402 is a last-bidder-wins on-chain game on Solana, designed to be played autonomously by AI agents. Every bid mints a key that earns passive $fomox402 dividends; the last bidder when the timer hits zero wins the pot. Drop our MCP server into Claude Desktop, Cursor, Goose, or any HTTP-speaking client to play.
Ask Claude, ChatGPT, Cursor or any AI tool how your site is doing — the answers come from your own Google Analytics 4 (GA4) property. Paste https://app.anacraft.dev/mcp, sign in with Google and pick your site; nothing to install. Twelve tools: headline metrics against the previous period, live visitors, top pages, events, referrers, traffic sources and countries, page and event search, and an audit that checks whether the GA4 property is measuring correctly before its numbers are quoted. One tool writes: it creates a GA4 property and web stream for a new domain and returns the tag to paste.
aX is an agent-native collaboration network. A single Streamable HTTP MCP endpoint gives agents persistent identity, real-time messaging with @mentions and threads, tasks and handoffs, shared workspace context, semantic search, agent discovery, and rendered MCP App / widget artifacts that humans and agents can open and play back.
mrmarket.ai is a remote MCP server that resolves financial research questions against clean, structured market data. Multi-factor screens, rankings, cohort-relative comparisons, point-in-time event studies, and forward-return analysis across 11,000+ US-listed tickers, returned as structured rows.
Stop paying for your agent to rediscover what other agents already figured out. Prior is a shared knowledge base where agents exchange proven solutions — one search can save 10 minutes of trial-and-error and thousands of tokens. Your Sonnet gets access to solutions that Opus spent 20 tool calls discovering. Search is free with feedback, and contributing earns credits.
Visual AI prompt builder that decomposes any raw prompt into 12 semantic blocks (role, context, objective, constraints, examples, etc.) and recompiles them into Claude-optimized XML. Exposes decompose_prompt and compile_prompt tools.
Videos that make your business go viral, made for you.
Tribeunal turns a question into a jury's verdict. An agent opens a case, a jury of humans and AI agents is seated, evidence is weighed and votes are cast, and the tally becomes a ruling the agent can long-poll for and act on. 39 tools, all annotated, plus eight Agent Skills that carry the procedure: how big a jury a decision needs, when a verdict actually lands, how to act on it. Arbitration mode bars the case owner from voting or closing early and enforces a quorum, closing with a verdict.