"PlayStation 3" matching MCP connectors:
GET /v1/connectors – MCP directory API referenceMatching Connector Tools:
CellMath is a governed AI memory and knowledge-cell MCP server designed to stop context bloat, unverified memory drift, and agent hallucinations. Instead of dumping raw, noisy RAG chunks into every turn, CellMath organizes persistent agent knowledge into structured, isolated Knowledge Cells with causal graph edges and strict write-time governance—keeping the full 3-tool MCP schema ultra-compact (~1,200 tokens). Core 3-Tool Pipeline: • vault_access — Read-only lookup, cell hydration, and graph edge traversal with strict zero-match silence (never fabricates context when no verified cell exists). • verify_safety — Preflight security and policy gate that blocks destructive or unsafe operations before execution. • vault_commit — Governed state mutation (store, update, causal edges, session checkpoints, and 4-tier purge) enforcing source provenance. Built for Claude, Cursor, ChatGPT, Gemini, and autonomous agents over Streamable HTTP.
Find AI-isms with evidence and fingerprint a writing voice from samples. 3 of 5 free.
Score video as an agent: cue sheet from the cut, 100+ AI instruments play your MIDI, mix to picture
Anime image generation for AI agents at $0.003 per image, one of the cheapest anime image APIs. Tools: generate_anime_image (anime $0.003, ultra $0.01, ultra-max $0.02 per image), generate_anime_video ($0.016/s at 480p, $0.04/s at 768p) and get_anime_video. Sign in with OAuth or send an API key as a Bearer header. Pay as you go from a prepaid balance (from $5, never expires, no subscription); new accounts get 3 free images.
Hybrid prompt-injection firewall (Llama Guard 3 8B + heuristics + Base64 decode) and Brazilian PII/secret masking (CPF, CNPJ, API keys). Supports x402 USDC on Base.
Hybrid prompt-injection firewall (Llama Guard 3) & Brazil PII/secret masking via x402 Base USDC.
Search 10k+ free CC0 3D models by meaning/size; generate and remesh from chat.
AI news for agents: daily, weekly and monthly briefings, trending events and model prices. No key.
Find your AI agent's likely failure mode, get runtime settings, and clarify ambiguous prompts.
AudD MCP is a way for agents to add music recognition to apps or to fulfill song identification requests. It connects you to AudD, the music recognition API
Veqen brings together work and coding agent costs per person and team, product inference costs per customer, agent spending, protection incidents, invoice checks, chargeback and the month-end close. Ask your assistant to investigate recorded spending, compare model prices, review provider keys and incidents, record bills and credits, or manage budgets, alerts, teams and spending policies. Your account role and plan govern access. Provider-key shut-off and agent-card controls require the appropriate role and provider permissions. Destructive actions require confirmation, and organizations can require a second person to approve a shut-off. SDK budget blocking is not a guaranteed spending cap. Work and coding agents are free for up to 3 people; product inference is free up to $1,000 in monthly AI spend. Connect your Veqen account for private organization data. The separate public model-price server needs no account. Estimates remain separate from provider invoices. Setup and permissions: https://veqen-app.com/docs/mcp
Developer fixes, free skills, browser tools and scoped technical services over MCP.
Veqen brings together work and coding agent costs per person and team, product inference costs per customer, agent spending, protection incidents, invoice checks, chargeback and the month-end close. Ask your assistant to investigate recorded spending, compare model prices, review provider keys and incidents, record bills and credits, or manage budgets, alerts, teams and spending policies. Your account role and plan govern access. Provider-key shut-off and agent-card controls require the appropriate role and provider permissions. Destructive actions require confirmation, and organizations can require a second person to approve a shut-off. SDK budget blocking is not a guaranteed spending cap. Work and coding agents are free for up to 3 people; product inference is free up to $1,000 in monthly AI spend. Connect your Veqen account for private organization data. The separate public model-price server needs no account. Estimates remain separate from provider invoices. Setup and permissions: https://veqen-app.com/docs/mcp
Axons Mobility is AI fleet management software with Intelligence and MCP. Ask about your scooter, bike, car sharing or golf cart fleet in Claude or ChatGPT. This public server answers product, pricing and trial questions with 3 help tools (no sign-in). Inside your own workspace, MCP gives 40+ fleet tools with role-based access, and nothing changes until a person confirms. https://axonsmobility.com
Onsite technical GEO visibility tests, score trends, sitemap discovery, and domain monitoring to ensure AI crawlers can access your site.
Authenticated async Opus 5.5 agent with status polling and artifact results.
Authenticated async GPT-6 Astra agent with status polling and artifact results.
Authenticated async GPT-6 Sol agent with status polling and artifact results.
Polymarket & Kalshi sentiment from X (Twitter) via Grok. Free daily scores; live scoring via x402.
A governed, nonclinical reasoning system that helps people and AI agents make sense of difficult moments and choose a grounded next step. Use Clarity OS for overthinking, emotional activation, uncertainty, decision friction, conflicting priorities, repeating patterns, or difficult conversations. It returns structured, safety-governed clarity while preserving uncertainty, personal agency, and appropriate nonclinical boundaries.
Formify turns document paperwork into something you can just ask for. Describe the agreement you need and it is built as a real, fillable PDF — text fields, checkboxes, dropdowns and signature space placed where a signing client actually expects them. Send it for electronic signature to one person or several, in a set order or all at once, by email or SMS, and preview exactly where every field landed before anyone is contacted. Prove who signed. Swedish BankID, an ID document scan, a live face check, or a company registration lookup for KYC and AML — including the option to capture an ID document's data without storing the image at all. Attach an AI assistant to the document itself. The recipient can ask it what a clause means and it highlights the passage it is answering about, reads it aloud if they prefer, and answers in English, Swedish or Spanish. They never have to paste your contract into another chatbot to understand it. Then track it. See who signed, who only opened it, and who never looked. Remind only the people who have not signed. Fix a mistyped email, hand someone a link in person, revoke a send, or download the completed document. Built for small businesses — agencies, property managers, trades, clinics and tour operators — where the person winning the client is also the person chasing the signature.
DePIN supply telemetry and network data with source, as_of, and verification links. Discover datasets, inspect provenance, and retrieve data through Streamable HTTP. Data access requires an API key.
Authenticated async GPT-5.6-sol Agent agent with status polling and artifact results.
Authenticated async GPT-5.6-luna Agent agent with status polling and artifact results.
Busca y lee miles de prompts y skills de IA en español, por profesión. Remoto o local.
AI landing page roast: score /100, 5-second test, top 3 conversion problems quoted from any URL.
Turn any Product Photo into a 3D model
AI 與科技名詞白話解釋:MCP、RAG、AI 代理人等名詞的白話定義。台灣繁體中文 MCP 工具。
台灣 AI 工具價格:AI 訂閱與 API 費用換算新台幣。台灣繁體中文 MCP 工具。
LLM & RAG evals: hallucination, eval contracts, semantic tests, tokens & model info. Free, no key.
OpenAI、Claude、Gemini 模型下架日、剩餘天數與官方建議替代,可檢查程式碼裡的模型。每筆附官方來源。
Non-custodial Solana & Base bounties ($0 gas onboarding), Lean 4 proof escrows & x402 AI video.
Use when choosing a SaaS, API or provider for a task: how far our agent got in each, sign-up to pay.
Remote MCP tools for 3-vendor AI workflow diagnostics, HAR sandboxes, 50v audits, and rubrics.
AI photo tools and 18 image models (GPT Image 2.6, Nano Banana, FLUX 3, more) over MCP. Pay per use.
Turn an uploaded photo into an AI video. Preview the credit cost and get the finished video link.
Search public tenders in China, inspect buyers, and estimate bid win probability.
Day-by-day AI travel itineraries with a self-critique pass for pacing and budget. Free for 3 trips a
15 tools, 38 languages, 8 AIs. Apple-approved 3-day Pro trial; subscription renews, no free Sends.
Can this LLM run on my GPU? VRAM, speed ceiling and what fits instead, for any model and GPU.
Read-only catalog of prompt packs and rule files: Cursor, CLAUDE.md, AGENTS.md, SKILL.md.
Free read-only Chinese AI news MCP: verified events, reports, products. No API key.
Energy impact of LLM quantization, calibrated to measured GPU data. Every answer states its basis.
Original comic strips of 3 to 6 panels with speech bubbles, from a story and characters you describe, in manga, cartoon, newspaper or graphic novel style.
Verified free AI credits, free tiers and startup programs, each with source link and verified date.
Will a QLoRA fine-tune of gemma-3-4b-it fit your GPU? Verdicts from measured AMD and NVIDIA probes.
Turn an idea or meeting transcript into a working single-file AI agent, check it, use it right away.
Find a free, ready-made AI agent for a task in the open agent registry (RAR).
Convert documents to structured JSON (invoices, receipts, contracts) in 2 seconds
The gap between Arena's #1 and #10 models fell from 148 points in Feb 2024 to 18. #10 now wins.
Anthropic has 7 of the top 10 creative writing models and Google 3. Meta's muse-spark-1.2.
Private SuperIntelligence by Mitosis Labs: define the term, see privacy layers, join the waitlist.
Discover AI agent insights, open research questions, and reproducible findings in a public commons.
Plan LLM fallback sequences from supplied cost, quality and latency assumptions; no live execution.
Estimate zkML proving and verification costs and latency from supplied measurements; no proofs run.
Since Jan 2024, Google's models have been #1 on Arena for 227 of 1003 days, third among labs.
Of 13 model launches from 23 Sept 2026 to 3 Oct 2026, 9 opened an API on day one, 7 of them.
Review agent task evidence with sample deduplication, version filters and uncertainty intervals.
Since Jan 2025, Arena's #1 spot has changed hands 16 times. Half of the finished reigns lasted.
Run deterministic SaaS contract redlining, GDPR Art. 28 DPA & EU AI Act compliance audits.