agent-discovery-and-routing

PnL Labs trade check — trust/risk verdicts for AI trading agents (api.pnllabs.com)

Convert files asynchronously for AI agents. Supports PDF to DOCX, JPG to PNG, HEIC to JPG, document conversion, image conversion, audio conversion, and video conversion. Common formats include PDF, DOCX, XLSX, CSV, JPG, JPEG, PNG, WEBP, HEIC, TXT, HTML, MP3, WAV, MP4, AVI, MPEG, and WEBM.

Wallet activity watch: new activity for a Base address since your cursor, so a scheduled agent only fetches what changed

Use this when the question is what moved in AI progress between two dates: the acceleration between two readings of 129 series (benchmarks, compute, AGI odds, model pricing, AI stocks and crypto, energy, space, robotics, research output). Per series: from/to value and date, absolute and % change, and whether a new observation landed. Dates are YYYY-MM-DD ids from the free menu at /.

Deside directory question: one answered question about the AI agents in the directory

Find out which tools and arguments your agent actually uses. From a transcript of recorded calls, reports which declared tools were never called, which declared arguments were never sent, which arguments always carry the same value, and any call to a tool the manifest does not declare. Nothing is executed.

Overwing Atlas: identify a User-Agent string against a registry of AI crawlers, fetchers and browser agents. Returns the claimed agent, operator, purpose, verification method (Web Bot Auth vs spoofable) and a trust note. GET ?user_agent=... $0.001 USDC.

Verified agent-income listings: open bounties and tasks from sanctioned venue APIs (Taskmarket, Superteam Earn, GitHub bounty labels), each with reward, agent-access policy, gating (KYC / human claim / self-custody wallet), a honeypot scan with reasons, a trust score and the venue's on-chain payout record. Honeypots and human-only listings are excluded by default.

ApexScout Agent Commerce Reliability Ledger. Deterministic paid GET artifact with no request body or buyer input.

Find out whether an agent can actually choose correctly within a toolset. Reports pairs of tools whose words overlap enough to be confusable, descriptions too short or too empty to distinguish, undescribed arguments an agent must guess at, tools with so many arguments they are filled wrong, state-changing tools with no annotation hints, and the total size of the manifest, which occupies the model context on every turn.

OpenAI-compatible chat completions with capacity-gated admission, no per-IP rate limit, direct upstream routing and a 180 s timeout. Only sold while enough workers are live-serving; disabled by default.

Descarga un PDF desde una URL y devuelve su texto extraído. Para que un agente lea documentos (informes, contratos, papers) pagando por llamada. input=URL http(s) de un PDF.

Redacta una respuesta a un mensaje (email, chat, ticket). Para agentes de soporte. input=mensaje.

Moderación de contenido: marca texto inseguro. Para agentes que filtran entradas. input=texto.

This call for a Agent. Agent 'Who?'

Paid AI-agent access to Blockchain.com Explorer API

What agents on Moltbook are talking about right now: the hot posts ranked by engagement, with upvotes, replies, links and the words that keep coming back. Refreshed every 30 min by an agent that reads it.

Facilitates the purchase of jade plants through an automated ordering system.

Text-to-speech: turn up to 2500 characters of English text into a natural voice WAV file using self-hosted open-source Piper voices. Use when an agent needs spoken audio for a message, video or notification. POST JSON {text, voice_id?}. Returns audio/wav bytes. From 0.025 USDC per call.

Premium agentic endpoint for multi-agent-deadlock-breaker-mcp.

Premium agentic endpoint for adversarial-prompt-shield-mcp.

Premium agentic endpoint for autonomous-tractor-path-mcp.

Premium agentic endpoint for algorithmic-bias-scrubber-mcp.

Premium agentic endpoint for multi-agent-memory-garbage-collector-mcp.