"Markdown MCP (Model Context Protocol) Server" matching MCP connectors:
GET /v1/connectors – MCP directory API referenceMatching Connector Tools:
SnapRender gives AI agents eyes on the web through a hosted MCP server. Send a public URL and get the page back as an image, a PDF or clean markdown, with no browser to run or maintain. Capture the viewport or the full page as PNG, JPEG, WebP or PDF, at desktop size or with a phone, tablet or laptop preset, in light or dark mode. Ads and cookie banners are removed by default, and you can hide elements or click one before the capture. extract_content reads the same page as markdown, text, article, links or metadata, so an agent can see a page and read it in one session. Made for monitoring and client work: batch up to 50 URLs in one job, check the cache for free before spending a capture, share signed links that render without an API key, and get webhooks when a batch finishes or a scheduled capture spots a change. Track competitors' pricing and landing pages, or send clients current screenshots of their sites. Connect with OAuth (Google, GitHub or email) or an API key. Works with Claude, ChatGPT, Cursor, VS Code and any MCP client. Free plan: 200 screenshots a month, no credit card. Paid plans from $9 a month for 2,000 up to $199 a month for 200,000. Home: https://snap-render.com Docs: https://snap-render.com/ai-agents
Search the web, fetch any URL and map a site as clean, LLM-ready Markdown.
Engram is a persistent, long-term memory layer for AI agents and assistants. Claude, ChatGPT, Grok, Cursor and any MCP client share one memory, stored as plain markdown notes: your knowledge base, second brain and AI context in one place. No extraction step: the memory is the note itself, so you can read exactly what your AI remembers and fix it. Edit your memory in Obsidian (real-time sync), the web app, or on your phone. Hybrid keyword + semantic search (RAG over your notes) finds exact strings like error messages, config keys and IDs. Remote MCP server over Streamable HTTP with OAuth 2.1; notes encrypted at rest. Https://engram.page https://youtu.be/rwnPeZ-8Lqo?is=NI-N7BduydGAiZlF https://github.com/engram-app/Engram
Publishes what an AI made — a page, a markdown or PDF doc, or a whole site — to a live HTTPS link. Runs locally over stdio from the @drop2run/mcp npm package, or hosted at https://mcp.dropto.run/mcp for chats that connect by URL.
MCP connector for ship modelling and scale modeling: explore detailed ship model builds, historical sailing ships, build logs, tutorials, galleries, and research content.
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.
AI-native task management: list, create, update and archive tasks with rich context for AI agents
ReelVision lets Claude, ChatGPT and other MCP clients watch short-form videos. Paste a reel link and the model gets the caption, a timestamped transcript and up to 20 keyframes, so it can explain, summarize or recreate what’s in the video. It can zoom into any timestamp to read small on-screen text or catch fast cuts. Works with Instagram, TikTok, Facebook and X. Built for designers and developers who save reels for inspiration and want AI to turn them into real work.
Multi-LLM entity enrichment: schemas, single/batch enrichment, fusion, model benchmarks.
Your AI assistant's creative studio. Make images, video, music and speech with Kling 4.0, Seedance 2.5, Nano Banana Pro, GPT Image 2.5 and more, billed at real model cost. A second brain learns from every generation and 100+ tested workflows, so results get better the more you make
Persistent context and memory vault for AI. Save your brand, project facts, prompts, skills and sessions once, then use them in Claude, ChatGPT, Cursor and any MCP client.
Makes on-model clothing photos for online stores: pick a model and scene, shoot, approve frames.
Load testing and synthetic monitoring platform: test with Playwright, Browser Bot, or Protocol Bots.
Markdown-based note-taking with a hosted MCP server. Your notes serve you and your AI.
Hosted MCP server for Indian NSE/BSE stock research: 59 tools for quotes, financials and ratios, peers, shareholding and pledge, filings with extracted facts, screens, F&O and FII/DII context. Source and freshness on every answer; no buy/sell calls.
Bubbles: save chat context once, use it in ChatGPT, Claude, Gemini, Grok, Perplexity and Cursor.
Second brain for investing. Investboard brings your portfolio, personal strategy and investment decisions together. Understand what you own, set out how you want to invest, and keep the reasons behind your choices. Bring that context into your AI assistant so each review can build on what you have already recorded. What Investboard can do: Investment Strategy Check: Assess proposed changes against your goals, allocation rules and constraints. Investment Decision-Making: Work through alternatives, trade-offs and uncertainty, and reflect on previous decisions. Investment Thesis: Develop and review your investment case, challenge its assumptions and define what would change your mind. Portfolio Intelligence: Explore your holdings, look through equity funds, identify overlap and concentration, and understand diversification and historical correlations. Connect your Investboard account to read your mandate, holdings, available analytics, saved checks, theses and journal entries. Try prompts like: - Help me understand my portfolio's underlying holdings, overlap and diversification. - Check a change I am considering against my investment strategy. - Help me develop an investment thesis and work through the decision. - Explain what my portfolio's historical correlations can and cannot tell me. - Review my recent investment decisions and the journal reviews that are due. - I decided to defer the change we checked. Record that decision. Connected features require an Investboard account, permissions and enabled sharing. Premium unlocks portfolio analytics, check history, thesis and journal reads. Requested hypothetical checks and stated outcomes are saved. The four companion skills also work with supplied files. Install them separately from [AI Toolkit](https://investboard.com/product/ai-toolkit). Update your strategy, save a thesis or complete a journal review in Investboard. You make every investment decision. Investboard does not place orders.
Image to SVG with a vectorization model we trained in-house. Clean, editable logos, icons, line art.
Persistent memory and shared context across compatible AI assistants, with account-scoped OAuth.
XMemo is a user-owned Memory OS for AI agents, providing a shared, persistent memory layer across AI assistants, IDEs, CLIs, tools, projects, and sessions. It enables ChatGPT, Claude, Codex, Cursor, Gemini, and other supported AI clients to access authorized long-term context without requiring users to repeatedly explain their preferences, project decisions, or previous work. Beyond basic memory storage and retrieval, XMemo supports semantic search, contextual recall, memory updates and corrections, source attribution, version history, project-scoped context, task tracking, and governed memory lifecycle management. Identity-aware access controls, scoped authorization, and memory isolation help users manage which agents and workflows can access their information. XMemo also provides advanced capabilities for structured knowledge, reusable procedures, and memory consolidation through its broader Memory OS platform. Connect through hosted MCP with OAuth or bearer-token authentication, or integrate directly through REST APIs and supported client tools. Memory remains available across authorized clients and sessions, with user-controlled access, export, and deletion. Website: https://xmemo.dev Documentation: https://xmemo.dev/docs
Pages, crawls and URL batches as clean Markdown and JSON for AI agents, with an Evidence Record.
Connect AI agents to shared Spaces for context, sourced work, tasks, and runs.
Send a PDF, a Google Doc or Markdown for e-signature from chat, and get the signed PDF back.
Marsell handles content, marketing and sales on autopilot for solo founders and small to medium businesses, with support for teams and organisations. This official remote MCP connector lets Claude, ChatGPT, Codex and other compatible AI agents work with your Marsell workspace. Read projects, brand context, market research, CRM contacts, analytics, content, plans and decisions waiting for you. Agents can also pick up homework, complete the work you request and report back to Marsell. With action-enabled access, they can update brand words, answer decisions and create pictures, with token costs quoted first. Connect to https://getmarsell.com/mcp using OAuth or a Marsell agent key. Choose read-only or action-enabled access; permissions are tied to the connected workspace, and access can be revoked in Marsell. No local server installation is required. Try the interactive demo: https://getmarsell.com/app/demo Setup and tool documentation: https://docs.getmarsell.com/developers/mcp
Vigilia watches your live app, explains every problem in plain language and writes the fix prompt. Your AI fixes it; Vigilia confirms with real traffic. Vigilia watches web apps that are live with real users, including apps built with Lovable, Bolt, v0, Cursor and Claude Code. It catches errors, failed requests and downtime, explains each problem in plain language, and writes a fix prompt for it. Connect Vigilia to Claude and ask what's broken. Claude lists your open incidents worst first. For each one it reads the plain-language diagnosis, who it affects, the technical evidence (error, page, failing request, stack frames and what the visitor did right before) and Vigilia's fix prompt. In Claude Code or another coding agent, Claude can then fix the cause in your own codebase. Once you've deployed, it marks the incident fixed, and Vigilia watches real traffic to confirm the error stayed away. If it comes back, the incident reopens as a regression. You can also ask how an app is doing (uptime, open incidents, today's traffic), get the exact install snippet for a new project, and check that a live site is running Vigilia. Vigilia never reads or changes your code: the fixing happens in your session, by your AI, in front of you. The only tool that changes anything is marking an incident fixed (the install check just records its result on the app), and you can connect with read-only access. Your data is stored in the EU. Emails, tokens and card numbers are stripped from what visitors' browsers send, and only that scrubbed error context is sent to Anthropic to write the diagnosis. Requires a Vigilia account. The free plan covers one app; reporting backend errors (Supabase, Next.js routes, Workers) is part of Pro.
Real-time Israeli rental listings, pricing estimates, and neighborhood intelligence across Tel Aviv and central Israel. Search 5+ deduped sources with hourly liveness, view specs, estimate fair-market rent, and explore local transit and area context directly inside your agent.
Connect your AI assistant to Blender for 3D modeling, Geometry Nodes, materials, lighting, animation, rendering and export. Inspect real scenes and viewport images, refine the result and restore checkpoints. OAuth connects your chat to Blender Bridge Desktop on an online Windows 10/11 x64 computer running Blender 4.2+. The chat can run on another device. Requires an active Blender Bridge account; 7-day trial available. AI model access is separate.
# **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.
Costory is the FinOps agent your team builds on. Claude plus a single provider's MCP works for one person and one cloud. It breaks when you add more providers, more people, and more tools to maintain. - Multiple providers: AWS, GCP, Azure, LLM APIs and data clouds normalized and allocated to teams and features in one model, including allocation from telemetry (Kubernetes, Datadog, dbt). - Multiple users: one hosted setup with OAuth, per-user access and enterprise SSO, instead of local credentials and prompts per person. - Maintained for you: tools, skills and connectors kept up to date by Costory, so reorgs and new services don't break your agent. Your agent finds savings, explains every change in spend and issues recommendations that your coding agent can implement. It works in Claude, Cursor and any MCP client, plus Slack. Customers include Alan, Deezer, Delivery Hero, Voodoo and Pennylane. Pricing: Starter from $300/month, flat: unlimited users and data sources, and a fair use that 80% of customers never outgrow. Nothing is ever cut off, and agents connected through the MCP use no AI credits. 30-day free trial.
Screenshots and clean markdown of any public web page, rendered in a real Chrome browser.
