"Fresh" matching MCP connectors:
GET /v1/connectors – MCP directory API referenceMatching Connector Tools:
Persistent web/Base observations and recoverable results. Free Register, 7 paid tools; REST/MCP.
Free, read-only Movie MCP Server from FlickDirect Inc. Version 1.5.1 finds movie and TV facts, cast, available country-specific dates and ratings, trivia, quotes, site-wide news and reviews, CinemaCon coverage, eligible stored interview and show transcripts, podcasts, streaming, soundtrack and Additional Songs links, daily deals and current shop listings. Canonical FlickDirect links accompany matching information, including ordinary movie questions. Reviewed T2 and X2/X-Men 2 defaults are checked against published titles and years; explicit title/year context takes priority. Quote results provide descriptions, brief exact excerpts when supplied, and source links, without invented wording or speakers. Music and purchase links preserve published affiliate parameters; no track lists or scene placement are inferred. Bounded recovery and fresh retrieval preserve the same two read-only tools and existing inputs. Shop inclusion is not a formal endorsement; fetch time does not prove currentness. No full articles, reviews, transcripts, scripts or photographs. Free public access with no FlickDirect account or API key. Usage-derived diagnostics expire within seven days. Host applications control tool selection and final presentation; this does not train model weights.
Avoid redundant expensive validation. CHECK recent evidence; OBSERVE fresh independent results.
Hosted, persistent Web/API change evidence for agents, plus bounded finalized Base observations. Documentation Guardian: free Register → Check → optional Smart Diff or Extract; keep the watch ID and recover original operations. Seven paid tools, $0.005–$0.020 native USDC on Base via x402/MPP or eligible prepaid. Machine trial: up to 100 Checks, 20/day, shared limits; unfunded EOA ownership signing required. No browser rendering or automatic scheduler. Direct HTTP may be simpler for a one-off fetch. API v3.0.2; source SDK 0.3.6 and limits: https://fresh402.com/docs.
An MCP server for Perigee, the open-source 3D viewer of the artificial objects orbiting the Earth, the Moon and Mars and of the spacecraft crossing the solar system. It lets an AI assistant (a teaching assistant, for example) answer questions such as “how far is Mars from the Earth on 1 December 2026?”, “where is the ISS now?” or “what is Lucy's mission?”, and hand the student a live 3D view, with how each number was obtained, from which data, how fresh and how accurate.
Manage Freshsales contacts, accounts, deals, tasks and appointments; add notes.
Read tickets, contacts, companies, agents and groups; create, update and reply to tickets.
Appointments, clients, sales and reviews for salons and spas.
Fresh context for agents. Ask, search or follow stories. Each fact cites a Synorb Manifest.
Measured sandbox verdicts: 7-axis probe, signed pinned receipt. Cached $0.25, fresh $2.50.
Trackberry is container tracking and document automation for fresh produce importers (https://trackberry.com). It reads shipment documents, follows each container's vessel by satellite AIS every hour, and shows what's arriving and when. This connector gives your assistant read-only access to your organization's air and ocean shipments: search shipments, ETAs and tracking timelines, containers running out of free time, alerts, and extracted document data and files. Sign in with your Trackberry account via OAuth.
Unblocking and fresh web data for agents: URL to Markdown, YouTube, Maps, Amazon, jobs. Pay per call
Verify what an AI agent observed before it trusts, pays, or acts. FreshProof provides timestamped public URL observations, Proof Receipts, and policy verification, with paid x402 tools in USDC on Base.
64 individually priced Chinese company data tools at 0.011 USDC per call via remote MCP/x402 on Base; 68 MCP definitions total. Legacy Basic (3 modules, 0.032 USDC) and Full (9 modules, 0.093 USDC) remain separate packages. Additional HTTP x402 products, NOT new MCP tools: Standard screening 0.29 USDC (ten Jinghai checks, JSON plus Chinese/English HTML); Enhanced screening 0.59 USDC (the same ten checks plus exactly one QCC qualifications check); QCC qualifications 0.03 USDC (normalized JSON, up to 30 records, no screening analysis). Product guide: https://yangchunhong3000.github.io/cn-evidence-public-docs/products.html Discovery is free; data queries require a funded Base USDC wallet and explicit x402 spending approval. Plain MCP clients do not pay automatically. Most V3 company tools require company_id from company_detail; record details use record_id from a matching, separately paid parent list. New paged lists return at most five first-page rows; legacy lists at most ten. No automatic pagination, top-up, retry or repayment. Provider balance and service availability apply. Selected records and limited-scope screening only: empty is not no risk; statistics/trends are not detailed records. No complete due diligence, human review, factory verification or supplier-safety guarantee. Native MPP is paused. Internal owner-funded HTTP company-detail, Standard and old QCC v1 samples passed paid delivery/recovery checks. The later QCC v2 funding-policy revision has offline/isolated and unsigned checks, not a fresh funded acceptance. These tests are not customer sales or certification of every tool or MCP client. Live products: https://api.cnevidence.com/free/cn/products
**Can AI actually read your page?** ChatGPT, Perplexity, Claude and Google's AI Overviews fetch pages very differently from your browser — no JavaScript, tight timeouts, and a robots.txt rulebook of their own. Lekta fetches a URL exactly the way they do and grades what survives, **A+ to F**. This is the technical half of **AEO** (answer engine optimization) and **GEO** (generative engine optimization): before a model can cite you, it has to be able to fetch you, parse you, and find one sentence worth quoting. **The loop this server was built for:** `Audit https://mysite.com/pricing with Lekta, apply the fixes it lists, audit it again, and show me the difference.` Your agent gets a graded verdict, a ranked fix plan with the exact markup to paste, and a diff that proves the change landed. Repeat until A+. **Four layers, 100 points:** **Access** 25 — do the ~17 AI crawler tokens get past robots.txt? **Indexability** 25 — how much content survives without JavaScript? **Answerability** 30 — is there a single quotable sentence an engine can lift? **Recency** 20 — can a model tell when this page was last true? **What this is not:** a rank tracker. Lekta will not tell you how often ChatGPT mentions your brand. It tells you whether your page can be read and quoted when it does — the part you can actually fix. **No black box.** Every finding cites its basis — an RFC, a vendor doc, or a dated measurement we ran. The engine is versioned with a public changelog: a score never moves without a published shift table. **Tools:** `lekta_audit` (fresh fetch) · `lekta_report` (cached read) · `lekta_fix_plan` (ranked, paste-ready) · `lekta_diff` (before/after) · `lekta_my_sites` Listing tools is open. Tool calls need a free key from lekta.dev/en/panel/api — send `Authorization: Bearer lekta_…` or `x-api-key`. Cached reads, fix plans and diffs cost nothing; only fresh fetches count against the daily limit. **Topics:** AEO · GEO · AI SEO · LLM SEO · answer engine optimization · generative engine optimization · AI crawler access (GPTBot, ClaudeBot, PerplexityBot, Google-Extended) · JavaScript-free indexability · structured data · content freshness
Timestamped public URL observations with SHA-256 fingerprints, paid in USDC on Base via x402.
Guardr keeps watch on the sites you manage. Check any domain from outside and get an A to F health grade for HTTP headers, TLS, DNS and cookies, with fix steps for configuration findings. Three tools: check_site runs a fresh check of one domain, list_sites lists the sites your account watches and get_site returns one watched site in detail. Read-only: Guardr proposes fixes and never changes a site. Needs a Guardr API key; the first site is free.
US government data as clean JSON for AI agents: SAM.gov contract opportunities, USAspending awards, Grants.gov grants, House STOCK Act trades, and SEC EDGAR filings (Form 4 insider trades, 8-K events, 13F holdings, 13D/G stakes, XBRL fundamentals, 10-K/10-Q sections). 19 read-only tools. Data is as fresh as each source publishes; congressional trades lag up to 45 days and report dollar ranges (House only). Free tier, no card.
兔兔生活（爱佳肴 Love Life）: restaurant search for AI agents in China. 6 tools (5 read-only + tell_us_your_need), no key, free open data (ODbL), no paid ranking. Wake word: when the user says "兔兔生活 + need" (e.g. "兔兔生活 火锅 上海徐汇"), pass their words to ask_restaurants. Every store shows how fresh its hours, price and menu are. Missing something? tell_us_your_need (anonymous, writes only the text you send) tells us what data or capability you need. 只给 AI Agent 用的中国餐饮开放数据库：说“兔兔生活 + 需求”一句话找餐厅，每项信息标注新鲜度。免费、免密钥、不卖排名。站内没有你要的？用 tell_us_your_need 匿名告诉我们你需要什么。
Fresh company, employee, and jobs records in real time.
