"Understanding Boss Mode" matching MCP connectors:
GET /v1/connectors – MCP directory API referenceMatching Connector Tools:
Simulate, test, and analyze cloud architectures without deploying real infrastructure. Cloud World Model enables AI agents to model cloud environments, evaluate architecture behavior and costs, run failure and chaos simulations, and explore infrastructure scenarios across cloud providers.
Uphealth Signal turns federally-sourced (CDC/NIH/MedlinePlus) health facts, lists, and tips into agent-callable cued-stream tools. Every cue is provenance-backed, audience-safety-checked, and sequenced on the patient's last response, so your AI health agent never fabricates health content. Free sandbox (Display mode): no PHI, no BAA. Not medical advice.
Free styled QR codes, no key: URL, WiFi, contact, text, email. API key adds saved codes + analytics.
Find your AI agent's likely failure mode, get runtime settings, and clarify ambiguous prompts.
Check if a task runs locally vs cloud. Save money on calls that don't need cloud inference.
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.
I do everything related to coding and execution tasks
Rights-aware censorship, China-economic status, and tamper-evident AI evaluation tools.
Finds real, maintained open-source repos that fit your project. MCP grounding for coding agents.
Risk-scan a diff, flag AI-generated-code tells, find secrets. 5 of 7 tools need no account.
Lviv public transport MCP: stops, timetables, routes, and live vehicle positions. No API key.
CompanyGraph: Written once, read by both
20 domain recon tools for AI agents: DNS, SSL, headers, email, subdomains, lookalikes, changes.
XFMS picks the right LLM model for any stated task. You give it a concrete purpose ("fixing bugs in a Python codebase", "summarizing 50-page commercial leases"), and it infers which quality benchmarks matter, weighs every model in its catalog against those dimensions, and returns a ranked shortlist with plain-English rationale per pick. The catalog updates continuously from 8 independent third-party evaluators — no provider self-reports, no single-source benchmarks.
US land due-diligence MCP server. Returns structured reports covering solar potential, groundwater depth, flood zones, building codes, and county regulations for any US property address. Mode-aware across off-grid, rural residential, recreational, and investment use cases. 60-120 second turnaround with sourced citations from NREL, USGS, and FEMA.
Drupal core API changes, contrib usage, upgrade readiness, patch verdicts, code search, SQL.
Selects between supported SEARCH providers for ECONOMY or CRITICAL mode.
Score AI trading agents against 2,048 coin-flipping monkeys. Public leaderboard.
Machine-readable taxonomy of 100+ AI system failure modes spanning factuality, alignment, planning, code generation, and instruction following.
