"Exploring Memory Persistence in DeepSeek Technology" matching MCP connectors:
GET /v1/connectors – MCP directory API referenceMatching Connector Tools:
Pugi is an AI product team in your chat. Describe a business in a few sentences and Pugi plans, designs, builds and checks a real website, shows a live preview, and puts it live on its own address. Ask for changes in plain words. Pugi also draws four whole logos for a business name with a brand kit, checks any public website or GitHub repository for leaked keys, vulnerable dependencies and risky code, and helps you start from public site templates. Sign in with a Pugi account (OAuth).
Shared project memory for AI coding agents: decisions, lessons, risks and tasks in one graph.
VAREXIS-INDEX — Source-Linked Evidence & Verification Tools for AI Agents VAREXIS-INDEX provides free, source-linked evidence for agent decisions through twelve focused guides and three distinct read-only MCP connectors. The original `/mcp` connector covers the approved search and preview population. The companion `/mcp/catalogue` provides deterministic access to 708 additional records by category and exact identifier. Configure both through the existing quickstart: https://varexis.tech/index-connect#quickstart Four optional one-time local checkers analyse supported customer-supplied declarations: Tool Admission £49, Audit Coverage £79, Data Exit £79 and Transaction Integrity £149, excluding VAT. These products do not independently inspect live systems, enforce permissions, establish payment settlement, verify deletion or certify compliance. Twelve free decision guides: https://varexis.tech/index-packs#free-decision-guides Read-only agent enquiry navigation (12 guides, 129 referenced records): https://varexis.tech/varexis-index/agent-entry.json Select a candidate guide, then follow the exact connector tool and identifier in the canonical manifest. Navigation does not establish applicability, a customer outcome or authority to act. Evaluate agent permissions, delegated authority, audit provenance, payment integrity, data retention and software supply-chain evidence before relying on documented claims. **FREE MCP CONNECTOR** Endpoint: https://varexis.tech/mcp Connect using Streamable HTTP. No authentication is required for public evidence discovery. Four free, read-only tools: - find_evidence_questions — Find existing reviewed evidence questions and matching routes. - preview_evidence_answer — Retrieve complete supported public answers, sources, limitations and snapshot hashes. - find_package_advisories — Find source-bound software advisory records. - get_index_access_options — Discover available services, pricing, licensing and purchasing requirements. Public MCP cannot execute actions, inspect private systems or authorise deployment. Developer quickstart: https://varexis.tech/index-connect **LICENSED VERIFICATION TOOLS** Four separately licensed, reusable local executables: **1. Agent Tool Admission & Permission Control — £49** Compare declared tool actions, resources, recipients and permissions across supported GitHub, Playwright, Notion and Slack integrations. Identify authority conflicts, missing verification and permission changes before human review. **2. Agent Audit & Evidence Coverage — £79** Reconcile declared identities, authorisations, actions and outcomes. Identify missing audit events, inconsistent references and unresolved export, retention or recovery evidence. **3. Agent Data Exit & Retention Reconciler — £79** Compare declared data inventories, exports, deletions, retention conditions and residual copies. Identify missing evidence and unresolved data-custody conditions during migrations and offboarding. **4. Agent Transaction Integrity & Replay Analyzer — £149** Reconcile declared spending authority, amended transaction terms, scoped idempotency keys, retries and reported outcomes. Identify conflicting purchase attempts and unresolved payment or entitlement evidence. All four products are separately licensed for reusable internal execution. Prices are one-time, exclude applicable VAT and do not include subscriptions, hosting or future updates. Checkers analyse supplied declarations locally. They do not independently inspect production systems, execute payments, enforce permissions, certify compliance or establish financial settlement. Explore all products, representative findings and free previews: https://varexis.tech/index-packs **FREE EVIDENCE PACKS** Seven complete public evidence packs cover: - GitHub and Playwright permission boundaries. - Notion and Slack access and data handling. - Audit and export evidence coverage. - Next.js advisory source assertions. - SonarQube, Snyk and Semgrep scanner trust. - Telemetry redaction and exception handling. - GitHub release approval and artifact identity. Source reviews include documented versions, provenance, exclusions and reliance boundaries. They are not independent deployment tests or current security certifications. 708 additional reviewed records are publicly available through exact-ID HTTP catalogue links and the separate read-only https://varexis.tech/mcp/catalogue connector. They remain outside the original MCP search and preview population and paid saved retrieval. Enhanced natural-language search for these additions remains on HOLD. Public catalogue: https://varexis.tech/varexis-index.json **SAVED EVIDENCE & SUBSCRIPTIONS** - Single Request: £5 — Save a version-bound published evidence result or obtain the eligible original Agent Tool Evaluation & Integration Kit. - Evidence Receipt: £19 — Add an unsigned delivery receipt to the eligible saved result. - Research: £29/month. - Developer/API: £149/month. Prices exclude applicable VAT. Subscription eligibility, rate limits and exclusions apply. The four separately licensed verification executables are not included in these existing evidence or subscription offers. **AGENT PURCHASING & RECOVERY** VAREXIS supports hosted Stripe checkout and compatible authorised MPP/Stripe Shared Payment Token purchasing through separate payment interfaces. Agent purchases require owner spending authority for the exact VAT-inclusive quote and any necessary provider authentication. Not every agent or wallet is supported. Public MCP remains free and read-only. Payment credentials and private customer data must not be submitted to the public connector. Existing purchases should be retrieved using the original credential. Uncertain payments must be investigated and recovered through supported procedures, not automatically purchased again. Purchase or recover: https://varexis.tech/index-access Agent payment contract: https://varexis.tech/varexis-index/agent-payments.json **WHY VAREXIS?** VAREXIS combines source-linked evidence, explicit limitations, versioned deliverables and structured verification of supplied declarations. Its purpose is to help agents and developers distinguish what available evidence actually establishes from what remains uncertain, unsupported or outside authority. Free evidence discovery. Transparent product scope. Reusable local verification. Bounded reliance. Website: https://varexis.tech Developer integration: https://varexis.tech/index-connect MCP endpoint: https://varexis.tech/mcp Additional optional connector: https://varexis.tech/mcp/guidance/v1. Configure it explicitly for get_decision_guide (exact published guide IDs) and check_tool_admission_fit (bounded, source-bound declaration-review suitability). Tool schemas and setup: https://varexis.tech/varexis-index/guidance-mcp-v1.json and https://varexis.tech/index-connect#bounded-guidance. The original /mcp four-tool connector and /mcp/catalogue two-tool connector remain distinct and unchanged. The additional tools are free and read-only; they do not execute actions, verify live permissions, grant entitlements or purchase anything. Missing or unbound applicability returns evidence-required. The existing Tool Admission price and licence remain unchanged.
Let AI agents read, check and edit Excel models. Open a workbook or drop in one MCP config. Either way: typed cells, a formula dependency graph, and a verification certificate. Deterministic — no OCR, no model guessing at your numbers.
Coding agents in multi-service codebases routinely rebuild existing helpers, trust stale type definitions, and modify API contracts without knowing who consumes them. Carrick solves this by indexing your entire TypeScript ecosystem across service and repository boundaries. By integrating deeply with the TypeScript compiler, Carrick traces every route, type, and cross-service call while recording function behaviour so agents search by intent rather than name. Delivered via MCP for AI agents and LSP for IDEs, Carrick ensures models see existing endpoints and utilities before generating new code. The scanner is source-available and runs from your CLI or CI pipeline.
Build, validate and deploy workflows as Cloudflare Workers in your own account, with approval.
Build it. Rehearse it. Own the room. The hosted MCP server for Kadal Deck (deck.kadal.cc), which has your back for the whole talk, from the first idea to the last applause. Connect once with OAuth and your AI agent can list and inspect your decks, read a talk in progress (current slide, who is watching, polls and questions by votes), check analytics, change titles, visibility and passcodes, roll back versions, create share links, and quick-edit and publish decks through the web builder, with conflict-safe publishing that never overwrites newer work. Pair it with the local server (npx @kadal/deck mcp) to write, check and build decks on your machine. Open source.
Free premium UI components in plain HTML, CSS and vanilla JS, for AI coding assistants.
TweakThis hands your coding agent the feedback left on your website. You or your client point at an element with the Chrome or Firefox extension and write a note; TweakThis captures the page, the element's selectors, HTML and styles, and a screenshot. Claude Code, Codex or any MCP client reads it over MCP, fixes it in your repository, and submits a resolution that you accept or reopen.
Live npm and UNPKG data for AI agents: package resolution, project audits, import maps, and malware/CVE checks. Optional Shield sign-in for domain data.
Writes your daily standup from GitLab or GitHub merge request state: what's ready, blocked or waiting on your review, and why a pipeline is red, read from the failing job log. OAuth sign-in, no API keys; can post the note to Slack, Discord or Google Chat on a schedule.
Create, list and check hrva.cc short links and read their click statistics. Sign in with your hrva.cc account over OAuth; every link goes through the same safety checks as on the website.
AI-native observability and security for engineering teams and coding agents. Search production logs in plain language, investigate issues and root causes, and create or edit live dashboards in your Sazabi workspace. Requires a Sazabi account (OAuth, or a secret key via the X-Sazabi-Secret-Key header).
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.
Give your AI assistant its own private email. Create mailboxes in seconds, send and schedule messages, and let the agent wait for incoming emails to pick up verification codes and confirmation links — without exposing your personal address. Works with Claude, ChatGPT, Cursor and VS Code: just sign in with your GhosterMail account. Requires GhosterMail Full Access.
Find leaked API keys, tokens and passwords in pasted text, see which are live, get a clean copy.
Form backend for static sites: create a form and get its HTML snippet, send submissions to email, Discord, Slack or a webhook, then read, moderate and clean up spam. Sign in with OAuth, no API key. MCP works on every plan, including Free.
Next cron run times in any IANA timezone, with DST gap and fold warnings.
Search the Amomic-AI docs and REST API for AI agents on calls, WhatsApp, chat and email.
See which AI models fall for traps in everyday jobs, and check or scan any MCP server, skill or package before your agent installs it. No sign-in; read-only; returns structured data.
Lets your AI build and edit websites in Xodia, a visual website builder for real code (Vite, React, Tailwind CSS or plain HTML in your own git repo): read and write site files, create pages and CMS collections, run typecheck, design and link checks, take screenshots, manage forms and translations, and pick up change requests the user sends from the visual editor. Sign in once with your Xodia account (OAuth). Free plan, no card needed. Setup: https://xodia.ai/ai/mcp
Search MakerRadar, a weekly product launch platform and startup directory: find products by keyword, platform, audience, use case or country, list alternatives, compare two side by side, and follow this week's or any past week's launch board. Signed in via https://api.makerradar.io/mcp/account, draft, edit and launch your own listing.
Frostbyte is a product planning workspace for founders and small teams who build software with AI coding agents like Claude Code and Codex. It keeps tasks, releases, ideas, user feedback and decisions in one plan. What's Next ranks what to work on, Project Health shows whether the release is on track, and your agent connects over MCP to read the plan and write progress, notes and decisions back.
Free vulnerability lookup and feeds for agents. Look up any CVE, GHSA or OSV ID, read vulnerability feeds filtered by technology, ecosystem, critical or CISA KEV, and check a lockfile for known vulns. Data is merged from the CVE List, GitHub Advisories, OSV, NVD, EUVD, CISA KEV, EPSS and Exploit-DB. No account or API key. Built by Sazabi.
Search and filter public CVEs and read any of them in full, with CVSS scores, CISA KEV and EPSS, and profile vendors. Read-only, free and open source, no API key needed.
Enhanciar is an AI company brain for every team. It reads your Slack, Gmail, Google Drive, Notion, Confluence, Jira, Linear, Zendesk, GitHub code and databases, writes a wiki from them, and answers questions from any MCP client with a link to the source. Tools: query (cited answers), search_wiki, get_page, list_pages, get_graph, get_process_map, impact (what a code change touches), list_repos, list_skills, get_skill, propose_action and list_proposed_actions (tickets, Slack messages, Gmail drafts, Notion pages and calendar holds that a person approves first). Hosted service, bring your own AI key. Plans: Solo $24 a month, Team $100 a month for up to 10 people. Create an API key in Settings at https://enhanciar.in.
Convert Apple Numbers (.numbers) to Excel (.xlsx) in the browser — first sheet free. MCP v1.1.0 (Streamable HTTP) exposes four tools: open_numbers2excel (open site / Stripe checkout intents; conversion is browser-local), get_site_info (product overview, pricing, URLs; read-only), get_pro_status (Stripe subscription_id sub_… status), get_unlock_from_session (Checkout session_id cs_… → entitlement). Path A: MCP does not accept or upload files.
HTML to PDF is a pain. Printed from a browser, your agent's Markdown report has no contents page with page numbers. legivel turns the same Markdown into a typeset PDF with one tool call. Invoices come from a saved template: JSON fills the fields, and a list or CSV fills the table. We generate the PDF in memory and never store the documents you convert or your PDFs. Templates you save are the exception: they are stored encrypted until you delete them. Ten tools, with an API key or MCP sign-in. 100 free documents a month and 3 saved templates.
kad.dev puts the apps you make with Claude on the web. You say what you want. Claude builds it and puts it online at its own address. You do not need to know how servers work. Your app gets its own web address. It stays private until you choose to share it. You can also use a domain name you own, like www.yourname.com. It can have a database that remembers what people enter, such as sign-ups, orders and notes, and storage for the photos and files your visitors upload. A Google sign-in lock lets in anyone with a Google account, or only the people you name. For a simple site, a change shows in a private preview within seconds, before it goes live. Every change you publish is saved as its own version, with its own private address. If something goes wrong, go back to an earlier one. If something breaks, Claude can read the error message, so it can be fixed in the same conversation. Access: you sign in with your kad.dev account and choose what Claude may do. Claude can always look at your apps. Changing or publishing them is a separate permission. Claude only sees your own projects. You can remove access at any time from your kad.dev account. Hosted in Europe. Requirements: a kad.dev account.
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
