Build and deploy AI agents on DataRobot. Supports LangGraph, CrewAI, LlamaIndex, and base agents with MCP server and React frontend bundling.

Set up CI/CD pipelines for DataRobot application templates with GitLab and GitHub Actions.

Upload datasets, manage data assets, and validate data for DataRobot workflows.

Instrument external agents with OpenTelemetry for DataRobot observability. Supports LangGraph, CrewAI, LlamaIndex, PydanticAI, and others.

Engineer features, run feature discovery, and analyze feature importance on DataRobot.

Deploy models, manage deployments, and configure prediction environments on DataRobot.

Explain model predictions, compute SHAP values, and run model diagnostics on DataRobot.

Monitor model performance, track data drift, and manage model health on DataRobot.

Train models, manage projects, and run AutoML experiments on DataRobot.

Make predictions, batch score, and generate prediction datasets on DataRobot.

A2A agent grounded in Joost de Valk's published posts and video transcripts. Answers natural-language questions about SEO, WordPress, the open web, AI, and open source, with a citation for every claim.

MCP server over Joost de Valk's writing on SEO, WordPress, AI, and the open web. ask_joost returns answers grounded in his posts and talks with source URLs; list_recent_content lists published posts filtered by topic and date.

REST API for registering schemas, circuits, and documents; submitting zero-knowledge proofs; and querying verified attributes. Agents use this API to integrate verifiable provenance into their workflows without handling plaintext data.

Verifiable provenance for AI agents — ZK proofs over confidential documents, no plaintext exposure. Register schemas, circuits, and documents; submit and query zero-knowledge proofs; verify attributes without revealing underlying data.

First stop in the Agentic Resource Discovery treasure hunt. Connect and call the tool to begin.

Export an entity's beneficial ownership and control graph as Beneficial Ownership Data Standard (BODS v0.4) statements in JSON, JSON-Lines or a zipped bundle (GET /export?lei=&format=json|jsonl|zip). Each entity statement carries the cross-reference identifiers GLEIF publishes against the LEI (BIC, MIC, ISIN, OpenCorporates, S&P CIQ, QCC) plus national company-register numbers, so the LEI connects to datasets worldwide.

Find a company's Legal Entity Identifier (LEI) from a name or a national company-registration number. Free-text fan-out search across GLEIF and connected registers (GET /search?q=&kind=entity), plus national-ID to LEI reverse resolution via GLEIF registration-authority codes. Use this first to obtain the LEI that drives the due-diligence lookup.

Run customer due diligence on a legal entity from its Legal Entity Identifier (LEI). Resolves the GLEIF record, fans out to 30+ national company registers and open datasets, maps results to the Beneficial Ownership Data Standard (BODS v0.4), and returns an ownership-and-control graph annotated with sanctions, PEP, debarment, offshore-leaks, FATF-jurisdiction and complex-structure risk signals. Primary endpoint: GET /lookup?lei=. Streaming variant for incremental results: GET /lookup-stream. Open data, no API key required.

Model Context Protocol server (streamable HTTP at https://api.opencheck.world/mcp) exposing OpenCheck as agent-native tools: opencheck_search and opencheck_resolve_national_id to obtain an LEI, opencheck_lookup for owners/controllers and sanctions/PEP/debarment risk, opencheck_export_bods for the BODS v0.4 ownership graph, and opencheck_list_sources. The most directly invocable surface for AI agents.

Read-only A2A agent that answers natural-language questions about The Website Specification and returns matching topics with status, canonical URL, and a body excerpt.

The entire specification as an Open Knowledge Format bundle: one Markdown concept per check, a mirrored concept per cited standard, plus index and change-log files. Browsable at /okf/ or downloadable as a single gzipped tar. The media type is interim and unregistered pending a blessed OKF media type.

Read-only MCP server exposing every spec page as queryable tools — search, list_topics, get_topic, get_checklist, get_categories — plus an audit_url prompt.

Agent Skill teaching a compatible agent when and how to query The Website Specification — the per-page Markdown over HTTP, llms.txt, and the MCP server. Served as SKILL.md (text/markdown, not a packaged zip) and discoverable via /.well-known/agent-skills/index.json.

Belarusian securities data: tokens, shares, bonds, companies.

Serves coding agents one canonical doc per query instead of rereading the repo. About 60% fewer tokens per doc lookup. Runs locally (SQLite + ONNX, no cloud); open source, by tsukumo.

MCP server for vreeman.com — search Simon Vreeman's technical-marketing tools (GA4 UTM builder, Measurement Protocol hit builder, CRO tools, experiment hypothesis builder) and Stoic philosophy library (Seneca's letters, Marcus Aurelius' Meditations, Epictetus' Discourses, Stockdale's essays, classic poems).

An Open Knowledge Format v0.1 bundle of this site's Stoic library — concepts, persons, works, and Seneca's letters as cross-linked Markdown — generated from the same data as the EntityMap.

Read-only OpenAPI description for public agent and developer resources.

Public MCP discovery metadata for Laisky services, blog content, and developer resources.

Instructions for agents that need to read Laisky blog content or discover Laisky MCP resources.