"A resource for conducting deep research" matching MCP tools:

• la_query

  Data La

  Run a raw SoQL query against any Los Angeles open-data resource (data.lacity.org) by its Socrata id (8-char like "2nrs-mtv8"). Full SoQL: where/select/group/order/limit/offset. Use la_datasets to find a resource id, or la_recent for the common ones.

  Connector

• verify_business

  BizVerify

  Confirm a specific, named business in one jurisdiction — the PRIMARY tool whenever the user wants to verify, check, confirm, or look up a company's existence, status, good standing, or details (e.g. "verify Acme LLC in Delaware", "is Acme registered in FL?", "I need to verify a company in Delaware"). If the user has verification intent but has not given the exact company name, ASK them for the name and use THIS tool — do NOT fall back to search_entities. Two tiers: quick (1 credit) returns existence + status + good-standing. Deep (15 credits, or 25 with force_refresh) adds entity type, formation date, registered agent, officers, principal address, and filing history. Deep is available in a subset of jurisdictions; requesting deep where unavailable returns a quick result with a reason. Requires authentication; deducts credits only on a successful match.

  Connector

• search

  Melvea Local Honey Discovery

  Search the Melvea local honey directory by free-text query and return matching producers as a list of results (id, title, url). Designed for ChatGPT Deep Research and Company Knowledge. Use for any local-honey discovery query that names or implies a place; the tool parses place and varietal from the query. Returns an honest empty list when nothing matches — never fabricate. Pair with fetch to retrieve full producer detail.

  Connector

• lion_deep_research

  LION x402 - Keyless Attested Enrichment & Signals for AI Agents

  ONE-CALL attested company/crypto deep research. Pass ?q=<company, domain, or topic> (and optional ?domain=, ?num=, ?receipt=1). LION runs web search -> scrapes the top source -> firmographics enrich (Wikidata + SEC) -> domain trust, and merges them into one Ed25519-attested JSON — replacing StableEnrich's 3-4 call research loop (~$0.08) with a single $0.012 call (~85% cheaper). For company research, vendor due diligence, business intelligence, SEC financials, and crypto/token research. Keyless, no account, no PII. For people/email/LinkedIn/maps use stableenrich.dev — LION proves companies. Volume: ?volume=100 -> $0.010, ?volume=1000 -> $0.008. [x402 paid tool: GET /api/x402/deep-research-json?src=mcp returns the 402 challenge with the canonical payTo; price 0.012 USDC on Base eip155:8453.]

  Connector

• convert_to_terraform

  Control Plane

  Convert a Control Plane resource manifest (YAML or JSON) into the equivalent Terraform (HCL). The manifest is first DRY-RUN VALIDATED against the API (no resource is created) — if it fails validation you get the error instead of HCL, so the returned Terraform always corresponds to a schema-valid resource. Pass `gvc` when the kind is GVC-scoped (workload, identity, volumeset). Set `generateImports` to also return ready-to-run `terraform import` commands. To convert an EXISTING resource instead of a manifest, use export_terraform.

  Connector

• get_resource_schema

  Control Plane

  Return the exact object schema and REST API endpoints for a Control Plane resource kind, so you can author an accurate manifest for `cpln apply` or call the API directly. ALWAYS call this FIRST whenever you are about to write a cpln apply YAML/JSON file, set up CI/CD that applies Control Plane resources, or build a request body for the REST API — do not hand-write a manifest or guess field names from memory. Pick a `kind` and pass `org` (and `gvc` for workload/identity/volumeset). Large schemas come back as a shallow map with deep sections collapsed to {"_expand":"<path>"} stubs; pass `path` (e.g. "spec.containers") to expand a section on demand. Server-managed fields (id/status/version/etc.) are already removed; `name` and `kind` are required at create.

  Connector

• get_nist_ai_rmf_requirements

  Stratalize Governance

  Use when conducting an AI risk management gap assessment, building board-level AI governance documentation, preparing for a model risk examination, or aligning an AI program with federal regulatory expectations. NIST AI RMF 1.0 is the US federal standard for AI risk management — adopted by reference in the Executive Order on Safe AI and aligned with Federal Reserve SR 26-2, OCC model risk guidance, and FDIC requirements. Returns all four functions (GOVERN, MAP, MEASURE, MANAGE) with categories, subcategories, and implementation guidance. Example: GOVERN function requires board-level AI policy, documented accountability structures, and AI risk culture assessment — the first control examiners check in a model risk review. Source: NIST AI RMF 1.0.

  Connector

• search

  DC Member API

  GET /search — Cross-resource omni-search Cross-resource search across profiles, rooms, messages (incl. private DMs + group DMs you're in), events, and chapters in one round trip. Returns the top-N matches per resource, grouped by resource. Use this when you don't yet know which resource carries the answer — agents typically call this first, then drill into a specific `GET /search/<resource>` for more depth on a single bucket. There's no page param: when you hit the per-resource limit and want more, switch to the per-resource endpoint for that one. The events slice has a baked-in forward-looking default (events ending in the last 30 days or later, and currently enabled) — this matches the in-app "Search across DC" surface. Use `GET /search/events` directly to look further back in time. **Query syntax (`q=`):** plain words match with prefix + typo tolerance. Wrap a phrase in double quotes to require an exact ordered match — e.g. `q="remote work"`. AND/OR/NOT/parentheses are NOT parsed in `q=` — use the structured filter params below for boolean composition.

  Connector

• delete_resource

  Control Plane

  Delete one Control Plane resource by `kind` + `name` — the single delete tool for every deletable kind. Deletes on the call (your client confirms the write first). Before calling, read the resource and tell the user what the deletion removes and which dependents break, and proceed only on their explicit approval. Deletion is permanent. Never invent a name.

  Connector

• resource_data

  Dane Gov Pl

  Read row-level data from a tabular resource (one with a tabular_data relationship). Returns JSON:API "row" objects whose attributes map column names (col1, col2, ...) to {repr, val} pairs. Supports paging and full-text row filtering via q. Use list_resources first to find a tabular resource id.

  Connector

• archive_provenance

  Colour Memory

  Explains the provenance of a named archive colour: documented fact vs computational derivation vs cultural interpretation, with confidence and citation format. This is one component of colour_passport, but also a standalone research tool for deep provenance work (museum, documentary, editorial). Use colour_passport for a general profile; call this directly for research workflows needing full source-chain detail.

  Connector

• image_personal

  Colour Memory

  Upload a portrait photo and receive a full personal colour analysis. Determines your seasonal type (Spring, Summer, Autumn, or Winter), colour depth (light, medium, or deep), and undertone (warm, cool, or neutral). Returns a curated palette of archive colours that genuinely suit you — each with full historical provenance and cultural context — plus colours to avoid. Uses Claude Vision for skin, hair, and eye analysis, then matches to the archive by CIEDE2000 perceptual distance. The photo is never stored. Example: a Deep Winter might wear Ottoman Carbon Ink while a True Spring suits Kogi Mango.

  Connector

• verify_references

  OpenWarrant — Document Verification Suite

  Fact-check a document's REFERENCES and CLAIMS — built for AI-generated reports whose citations must be checked before they're trusted. USE THIS WHEN someone shares a report, article, whitepaper, or deep-research export (or a link to one) and asks: is this accurate / legit? are these citations real? fact-check this. did the AI make this up? Also use it proactively before relying on any AI-written document. Provide the document ONE way: `url` (a public http(s) link to a PDF or web page — fetched server-side, the cheapest call: no need to download or encode anything), `text` (pasted markdown/plain prose), OR `bytes_b64` (a base64 PDF; URLs are read from the PDF's link annotations, so they're exact). Default (fast): provenance (is it a ChatGPT deep-research export?), citation resolution (live / archived / dead, papers matched against arXiv/Crossref to catch 'real ID, wrong paper'), and internal MATH (recompute the doc's own arithmetic). Set `deep=true` to also fetch each cited source and judge whether it SUPPORTS or CONTRADICTS the claim (slower, ~a minute). Returns a trust summary, per-item tables, and a shareable `permalink` to the public fact-check record. HONEST BOUNDARY: this reports verification COVERAGE, not truth — 'supported' means evidence-backed (not necessarily true) and 'unsupported' means no evidence found (not necessarily false). It tells a reviewer WHERE to look; it does not bless the document, and it never affects the fraud risk band.

  Connector

• search

  SocialGPT

  Search across your own connected-account content and return the best matches. Each result has an `id` (pass it to `fetch` for the full item), a `title`, a `url`, and a `text` snippet. This is the deep-research "search" entrypoint the ChatGPT/Claude connectors call by convention; for semantic search over analyzed videos specifically use `search_videos`. Returns {"results": [...]}; when you have no connected accounts it returns reason="no_connected_accounts" plus a connect_url instead of results.

  Connector

• kcmo_query

  Data Kcmo

  Run a raw SoQL query against any Kansas City, MO open-data resource (data.kcmo.org) by its Socrata id (8-char like "vsgj-uufz"). Full SoQL: where/select/group/order/limit/offset. Use kcmo_datasets to find a resource id, or kcmo_recent for the common ones.

  Connector

• montreal_query

  Data Montreal

  Query any City of Montreal datastore resource (donnees.montreal.ca, CKAN) by its resource id (a UUID). Supports a free-text `q`, exact-match `filters` (field→value), `sort` ("field desc"), limit and offset. Use montreal_datasets to find a resource id, or montreal_recent for the common ones.

  Connector

• austin_query

  Data Austin

  Run a raw SoQL query against any Austin open-data resource (data.austintexas.gov) by its Socrata id (8-char like "fdj4-gpfu"). Full SoQL: where/select/group/order/limit/offset. Use austin_datasets to find a resource id, or austin_recent for the common ones.

  Connector

• get_resource

  Control Plane

  Fetch one Control Plane resource by `kind` + `name` (no `name` for kind="org"). Returns a summary plus the full JSON. The single read-one tool for every resource kind. Secret values are masked — use reveal_secret to read them. Call this before any update or delete to capture current state.

  Connector

• explain_architecture

  Zephex

  Structural wiring map — how files connect, not file bodies. Returns concern_cluster (roles + import edges for ANY subsystem label), layer_map, entry_points, integration_map, auth_flow, request_flows in deep mode, Mermaid. CALL WHEN: how does this feature/subsystem work across files before a cross-cutting edit; pass concern (any name: widget-factory, billing, q7x) or seed_files from find_code — seeds via concept search + import graph, not hardcoded vocab. DO NOT: stack/scripts (get_project_context), search (find_code), read bodies (read_code). focus: api|auth|integrations|database|security|full. mode: overview|deep|audit. subpath for monorepos. Path: absolute dir or github:owner/repo.

  Connector

• fetch

  DC Hub — Data Center & Power Intelligence

  Fetch a DC Hub record for an id returned by the `search` tool (OpenAI Deep Research / ChatGPT connector format). Returns {id, title, text, url, metadata} — a citable public summary of one data-center facility (name, operator, location, status, market). For full structured specs (capacity MW, coordinates) use get_facility or open the url.

  Connector