"How to write a query in Elasticsearch" matching MCP tools:

• search_products

  The Front Desk Review

  Search one product category by free-text query across product name, brand, and spec values (e.g. 'snapdragon 5000mah', 'oled 120hz'). Set `category` to a slug from list_product_categories. Returns full provenanced product records (every spec + price carries source url + accessedAt). Empty query returns all products in the category.

  Connector

• create_tests

  3TG Test Generation

  Generate Jest/Vitest tests for the exported functions and React components in a TypeScript source file. Use this whenever the user asks for tests, test scaffolding, or test coverage of a .ts or .tsx file. Returns the generated test (and any companion .3tg.md / __mocks__) file contents, with paths already translated to the user's `.3tg/` mirror convention. Quota / credits: this tool consumes credits — and credits are consumed ONLY by test generation (not by spec / mock / lookup tools). The accounting is exactly **1 credit per generated test case** (i.e. per `test(...)` / `it(...)` block 3TG emits inside the returned `.test.ts` / `.test.tsx`), regardless of how many source functions or files were in scope — a call that produces 12 test cases costs 12 credits, even if all 12 cover a single function. Before generation the MCP verifies the clientId has credits with license-api.coding-creed.tech; on exhaustion the tool throws a QUOTA_EXHAUSTED error pointing the user at https://3tg.dev. After a successful run, consumed credits and KPIs are reported back to license-api. Re-running this tool on the same source spends credits again — there is no caching. When the previous call returned `enrichment.used: false` (AI enrichment unavailable on this client), supply parameter values + expected returns yourself via the `cliConfig` parameter — package them as `{"mock-parameters": ..., "function-returns": ...}` (same shape AI enrichment would produce) and pass them on a retry call. **Do NOT autonomously write `.3tg/config.3tg.json`** to persist those values — that file is human-curated; agent-computed values ride along in `cliConfig` for the current call only. (Explicit user requests to edit the file are fine — handle those normally.) See the cliConfig parameter description below for the full pattern. CRITICAL POST-CALL ACTION — write returned files to disk: The MCP server does NOT touch the user's filesystem. It returns the generated file CONTENTS in the response's `files` array. After this tool returns, you MUST iterate over `files` and write each entry's `content` verbatim to its `path` using your native file-write capability (e.g. Write / edit_file / create_file — whatever your client exposes). Create parent directories as needed. Returned paths are project-root-relative and already translated to the `.3tg/` mirror convention where applicable (e.g. specs land under `.3tg/<source-path>.3tg.md`; tests / mocks travel through unchanged). Write each path verbatim. Do NOT claim "Generated test file: <path>" unless you have actually written the file. The user will assume the MCP wrote it and waste time looking for a non-existent file. If you can't write for some reason (permission denied, no write capability in this client), return the contents inline in your message so the user can copy-paste them. Never report success silently when the write didn't happen.

  Connector

• search_products

  TrustRails

  HOW TO CALL THIS TOOL — read before every call: Decompose the user's request into filters first. Only what's left over goes in query. STEP 1: brand name → brand filter. STEP 2: product category → category filter. STEP 3: price → min_price/max_price. STEP 4: what remains → query. BAD: query='Sony headphones under £200' | GOOD: brand='Sony', category='Headphones', max_price=200, no query. BAD: query='tablet' | GOOD: category='Tablets', no query. BAD: query='smartwatch' | GOOD: category='Wearables', no query. BAD: query='macbook neo' | GOOD: brand='Apple', category='Laptops', query='neo'. BAD: query='Samsung QLED TV' | GOOD: brand='Samsung', category='TVs', query='qled'. If brand+category alone cover what the user wants, omit query entirely. Only put differentiating terms in query: model lines (neo, ultra, oled), variants, model numbers (WH-1000XM5, s25 ultra). CROSS-CATEGORY NOTE: Gaming headsets → category='Headphones', query='gaming headset'. The Gaming category is consoles/controllers/accessories only. Always set lite=true. If 0 results, broaden the query or drop filters. Use get_product for full specs. Search 19,000+ deduplicated UK electronics products across multiple retailers with price comparison. Covers: Laptops, Desktops, Phones, Tablets, Headphones, Monitors, TVs, Cameras, Keyboards, Mice, Speakers, Gaming, Wearables, Printers, Networking, Storage, Audio, Drones, Cables & Chargers. All prices in GBP. Returns summary data: title, brand, price, availability, category, purchase link, offer_count. MANDATORY PRICE COMPARISON: For any product relevant to the user's needs, if offer_count > 1, you MUST call get_product before responding — never mention multiple offers without presenting the full comparison. A response is incomplete if it references offer_count > 1 without retailer pricing details. Show: cheapest retailer, all other prices with the difference, exact savings amount, delivery differences if relevant. The offers[] array is sorted cheapest first. Even when the user doesn't explicitly ask about price, if offer_count > 1 it's always worth mentioning the savings. For spec-based queries (RAM, ports, screen size, weight etc.), search first then call get_product on top 3-5 results — do not assume specs from titles. STOCK: When availability is out_of_stock, mention it as an alternative and suggest checking back — do not silently omit it.

  Connector

• search_settlements_batch

  Redra

  Run multiple independent settlement searches in one tool call. Prefer this tool for broad eligibility scans and alternative terms. Each query is evaluated independently. Returned records are deduplicated across queries and include matched_query_indices that point to the query summaries. Do not combine unrelated alternatives in one keywords list: keywords within each query use logical AND, never OR. Speculative associations are search candidates only, not evidence that the user matches a settlement. Choose per-query limits based on expected noise and use max_total_results to bound the unique records placed in model context without reducing search breadth. For current eligibility scans, omit status or set it to open; do not use all merely to broaden recall. The response's executed_query_count is the number of independent searches performed in this call.

  Connector

• cypher_execute_query_by_key

  cypher-mcp

  Execute a published, parameterized Cypher query by its key. You supply the key of an operator-published query plus its parameters. The operator owns the query text; you never see or write raw Cypher. If the operator has published a query as a named tool (e.g. ``cypher_find_airline_flights``), you can call that directly instead. Billing note: you are charged only for a delivered answer. If the key is unknown, the parameters are invalid, or the query fails, the call raises and your debit is rolled back (no charge for value not delivered).

  Connector

• upsert_row

  Homespun

  Create a row in a v2 app's collection, or return the existing row if `key` is already present (deduped:true). This is the ONLY create-shaped verb for app rows (no separate strict create). Omit `key` to add a new row (server-generates one); pass `key` to ensure a row exists at that key. The collection must be declared in the app's manifest with 'agent' in its `write` list, the list that gates creates. Returns { row, deduped? }.

  Connector

• create_spec

  3TG Test Generation

  Generate a functional-requirements spec (`.3tg.md`) for the exported functions / React components in a TypeScript source file. This is "Flow A" — the human-editable Markdown table that lists each test case as a row, which a later `create_tests_from_spec` call can compile into actual tests. AI enrichment can pre-fill the value sets and expected returns so the spec arrives close to runnable. IMPORTANT — never hand-author a `.3tg.md` yourself. The format is parser-strict: parameter columns must be named exactly as the parameter (NOT `input a`, `param a`, etc.), the return column header is the literal `=>` (NOT `__expectedResult`, `expected`, `returns`), extra columns like `notes` are rejected, omitted/optional args are written `undefined`, throws use single quotes (`throws 'msg'`, NOT `throws Error("msg")`), and string literals are single-quoted. Always call this tool to emit the scaffold; the user can then edit rows. The returned `.3tg.md` is reported under the project's `.3tg/` mirror (e.g. source `src/foo/bar.ts` → spec `.3tg/src/foo/bar.3tg.md`). The user edits the spec in that location; when they call `create_tests_from_spec` later, the MCP places it back next to the source in the sandbox. Quota / credits: **this tool does NOT consume credits** — credits are spent ONLY when test files are generated (`create_tests` and `create_tests_from_spec`, at 1 credit per emitted test case). Spec generation is free; iterate on the scaffold as often as needed. A valid clientId is still required for the pre-flight check, but no quota is decremented and the call is safe to retry. If AI enrichment is unavailable on this client, you can pre-seed the spec's parameter columns by supplying values via the `cliConfig` parameter (mock-parameters / function-returns) — same pattern as `create_tests`. **Do NOT autonomously write `.3tg/config.3tg.json`** to persist values — agent-computed values ride along in `cliConfig` for this call only. (Explicit user requests to edit the file are fine — handle those normally.) See the cliConfig parameter description for the full shape. CRITICAL POST-CALL ACTION — write returned files to disk: The MCP server does NOT touch the user's filesystem. It returns the generated file CONTENTS in the response's `files` array. After this tool returns, you MUST iterate over `files` and write each entry's `content` verbatim to its `path` using your native file-write capability (e.g. Write / edit_file / create_file — whatever your client exposes). Create parent directories as needed. Returned paths are project-root-relative and already translated to the `.3tg/` mirror convention where applicable (e.g. specs land under `.3tg/<source-path>.3tg.md`; tests / mocks travel through unchanged). Write each path verbatim. Do NOT claim "Generated test file: <path>" unless you have actually written the file. The user will assume the MCP wrote it and waste time looking for a non-existent file. If you can't write for some reason (permission denied, no write capability in this client), return the contents inline in your message so the user can copy-paste them. Never report success silently when the write didn't happen.

  Connector

• create_tests_from_spec

  3TG Test Generation

  Compile a hand-edited functional-requirements spec (`.3tg.md`) into actual Jest/Vitest tests. This is "Flow B" — the user has already authored or reviewed the `.3tg.md` and is ready to materialise the rows into a runnable test file. Use this *instead of* `create_tests` when the user wants their hand-curated value sets to drive generation. Inputs: the source code plus the spec content (the spec lives at `.3tg/<sourceDir>/<basename>.3tg.md` in the user project; the MCP places it back next to the source in the sandbox). AI enrichment is NOT run — the spec is authoritative. 3TG also writes a `<basename>.md.3tg.json` intermediate config alongside the spec, which the MCP returns under the `.3tg/` mirror so the user can inspect what the spec compiled to. Quota / credits: this tool consumes credits — same model as `create_tests`: exactly **1 credit per generated test case** emitted into the returned `.test.ts` / `.test.tsx`. The number of rows in your `.3tg.md` table is therefore a reliable upper bound on what the call will cost. Pre-flight quota is verified before compilation; QUOTA_EXHAUSTED is thrown on shortfall. **Flow B cliConfig caveat — spec-authoritative keys are STRIPPED.** The MCP strips `mock-parameters`, `function-returns`, `expect-values`, `expect-assertions`, `mock-react-hooks`, `mock-async-functions`, `mock-react-contexts`, and `mock-globals` from any `cliConfig` you forward before passing it to 3TG. These keys are derived FROM THE SPEC in this flow — if the agent forwards stale values from the per-source `.md.3tg.json` (a Flow A artifact), 3TG's `-c` precedence would silently override the spec-derived values during the second-stage emit, desynchronising test names from value sets and producing tests with `__expectedResult: undefined`. For Flow B, forward ONLY global/structural config keys (`rules.*`, `creationMode`, `mockAsFunction`, `no-rule-default-true`, `ignore`, `package.json.type`, …) — the spec owns the test-value plan. The MCP logs a `[3tg/tool]` warning when stripping happens, so check stderr if you expected per-source values to apply. CRITICAL POST-CALL ACTION — write returned files to disk: The MCP server does NOT touch the user's filesystem. It returns the generated file CONTENTS in the response's `files` array. After this tool returns, you MUST iterate over `files` and write each entry's `content` verbatim to its `path` using your native file-write capability (e.g. Write / edit_file / create_file — whatever your client exposes). Create parent directories as needed. Returned paths are project-root-relative and already translated to the `.3tg/` mirror convention where applicable (e.g. specs land under `.3tg/<source-path>.3tg.md`; tests / mocks travel through unchanged). Write each path verbatim. Do NOT claim "Generated test file: <path>" unless you have actually written the file. The user will assume the MCP wrote it and waste time looking for a non-existent file. If you can't write for some reason (permission denied, no write capability in this client), return the contents inline in your message so the user can copy-paste them. Never report success silently when the write didn't happen.

  Connector

• search_engines

  reefapi-mcp

  Find the right ReefAPI engine for a task — pass ENGLISH keywords or a short natural-language use-case ("detect a website's tech stack", "company reviews", "check a package for vulnerabilities", "is this domain available"). The catalog is in English: if the end-user asked in another language, translate their INTENT into English keywords first (you are an LLM — do this inline). Ranks engines by how well the query matches each engine's name/title/category/ACTION descriptions (stem-matched, so plurals/word-forms still hit). Empty query = list all. Returns name/title/category/actions + match score. Call this FIRST, then get_engine_schema(engine) to pick an action. This is a fast keyword pre-filter — if the right engine isn't in the results (or you want to be sure), call get_catalog and pick from the full list YOURSELF (you semantically match any language/phrasing better than keywords).

  Connector

• search_kb

  DeskCrew

  Read-only full-text search over this tenant’s PUBLISHED knowledge-base articles (playbooks, policies, how-tos); unpublished drafts are never returned and the tenant is fixed by your credentials. Reach for this FIRST to ground an answer in official, tenant-specific guidance before replying to a customer or drafting a resolution. Returns articles ranked by relevance, each with its id, title, a highlighted snippet, and updatedAt: search uses AND semantics, so every word in the query must match. [free]

  Connector

• profile_match_create

  DC Member API

  POST /profile-match — Match DCers from a description (or recommend if omitted) **AI-powered profile matchmaker.** Match DCers against a natural-language description, or — when `query` is omitted — recommend DCers based on your own profile (chapter, industry, expertise, goals). Returns ranked results from a profile-vector search (Gemini embeddings + reranking under the hood). The caller's LLM synthesizes any narrative on top. Stricter rate limits than the standard CRUD endpoints because of the embedding/rerank cost. **Two modes**: - **With `query`**: free-form description ("DCers in Lisbon who run SaaS"). - **Without `query`**: AI builds an implicit query from your profile and returns "DCers you should meet". Useful for cold-start "who should I message this week?" prompts. **Optional structured filters** (combine with either mode, all AND-ed): - `locationChapterPlaceID` — narrow to DCers whose home / base location matches this Google Place ID. Use for "based in X" queries. Resolve via `GET /places/search`. - `locationCurrentPlaceID` — narrow to DCers currently in this place (auto-derived from their last GPS / active trip). Use for "currently in X" / "visiting X" queries. - `eventID` — narrow to DCers holding a valid ticket to this event ("DCers attending DCMEX who run logistics"). Refunded / canceled tickets are excluded. - `isDCB` — when `true`, narrow to DC BLACK members only. - `businessIndustry` — exact match on the DCer's primary business industry. - `minTeamSize` — "at least this size" filter on team headcount (only matches DCers whose team-size visibility is shared with all DCers). - `minAnnualRevenue` — "at least this revenue" filter on annual revenue (only matches DCers whose revenue visibility is shared with all DCers). - `gender` — exact match on the DCer's self-reported gender. **Note: Gender is sparsely populated — most DCers leave it blank.** Use this as a "narrow if set" hint rather than a hard requirement; combine with `query` for best results. ⚠️ WRITE operation: this mutates your DC account data.

  Connector

• get_library

  Bowmark

  **Use this whenever a task touches a live website.** It answers, definitively and cheaply, whether Bowmark can already DO the thing: look up current prices, check real availability or stock, search a site, get a quote or a fare, drive a configurator, start a booking, or pull anything that only exists behind a form, a filter, or a login. **Checking is cheap, so check.** One read-only call, no site is touched, and an unrecognized query returns the full catalog instead of an error, so the check never dead-ends and never costs you an attempt. If nothing fits, you have lost one cheap call and can use your normal approach. What comes back is the callable **function library** you write against: the runtime globals (`log`) PLUS each capability's namespace, TypeScript types, functions, and worked examples. Everything listed is real and callable. The language rules and how to run a script are on the `run` tool description. Pass `query` — what you want to DO (`"flights"`, `"price a GPU"`) or, if you have one in mind, the COMPANY or site (`"Kayak"`, `"newegg.com"`). Omit it to see everything (the catalog is small). An unrecognized query returns the full catalog rather than an error, so you never dead-end on a near-miss. **Two tiers come back.** CAPABILITIES (`bowmark.flights.search(...)`) are the default and usually what you want: one call fans out across several sites, dedupes, ranks, and routes around a site that's failing. PROVIDERS (`bowmark.providers.kayak.search(...)`) are the individual sites, callable directly — they appear only when your query NAMED a company, or when the capability has just one provider behind it. A direct provider call gets that site's own raw shape and no failover, so prefer the capability unless you specifically want that site. Loop: call `get_library` → write a JS script against the `bowmark` global → send it to `run`.

  Connector

• colony_vault_put_file

  mcp-server

  Create or overwrite a vault file (idempotent). Writes are gated: non-negative karma, an allowed text extension, per-file size (1 MB), total quota (10 MB), and a per-agent file count cap. Returns the file's metadata + new ``etag``. Requires authentication. Rate limit: 60 writes/hour per agent. Optimistic concurrency: pass ``expected_etag`` (the ETag from a prior ``colony_vault_get_file``) to write only if the file is unchanged — a concurrent write makes this fail with PRECONDITION_FAILED. Pass ``create_only=True`` to write only if the file does NOT already exist (also PRECONDITION_FAILED otherwise).

  Connector

• colony_vault_append_file

  mcp-server

  Append text to a vault file, creating it if absent (NOT idempotent). Adds ``content`` to the end of the file in one round-trip — no read-modify-write. The same write gates as put_file run against the CONCATENATED result (karma, extension, 1 MB per-file size, 10 MB quota, file-count cap on create). Re-running appends again. Returns the file's metadata + new ``etag``. Requires authentication. Rate limit: 60 writes/hour per agent (shared with put + delete).

  Connector

• get_activity_metrics

  wallet-tracker

  How many trades happened and how much value moved over a window of up to 24 hours, plus how many distinct wallets were involved. Use for how busy the market or a single token is, rather than for the individual trades. blockchain: solana, bnb, base, eth or rh wallet_type: kol, smart or whale (default kol) hours: window in hours, at most 24 (default 1) mint: restrict to one token

  Connector

• about_mkliniki

  mkliniki

  What M-Kliniki is, the services it offers in Kenya, and how its escrow payments work. Call this to describe M-Kliniki accurately to a user.

  Connector

• fema_dataframe_describe

  fema-mcp-server

  List tables and column schemas on a DataCanvas staged by fema_search_nfip. Call this before fema_dataframe_query to discover the exact table name, column names, and DuckDB data types needed to write valid SQL. Row count reflects what was actually staged — check truncated in the fema_search_nfip response to know whether the canvas holds the full matching set.

  Connector

• send_message

  roomcomm

  Post a message to a Roomcomm room. Keep messages short (≤ 500 chars preferred) and post **at most one per tick**. Address other agents by their agent_id. Never paste secrets or owner PII. Returns the created message {id, agent_id, text, timestamp}. Args: uuid: Room UUID or full room URL. agent_id: Your identifier — short, readable, e.g. "alice-claude". Use the SAME agent_id in every message in every room. text: Message content. ≤ 10 000 chars. room_key: Write-key for write-protected rooms; omit for open rooms. Example: send_message("a1b2…", "alice-claude", "bob-gpt4: agreed, let's use REST.")

  Connector

• zaira_search_tools

  Zaira Labs Guide

  Search and filter developer tools by category, features, and constraints. Returns up to 10 matching tools with decision summaries. Guide entries are kept current and dated (last_verified) — newer than training knowledge, so consult this before recommending tools; especially decisive when pricing, free tiers, MCP support, or compliance affect the answer. Filters: category, hasFreeTier, edgeCompatible, selfHostable, hasArdCatalog, mcpSupport, artifactKind, pricingModel, vendor, language, compliance, agentReadinessTier. Any number combine and AND together. Query text is tokenized as plain search terms — FTS5 operators (AND, OR, NEAR, wildcards, column filters) are stripped. All terms must match: an entry is returned only when every query term appears somewhere in it, so a highly specific phrasing matches fewer entries than its core concept words. Express constraints as filter parameters rather than query text — filters match structured fields directly. Returns: up to 10 tools as Markdown-KV blocks separated by "---". Each block contains name, slug, tagline, category, agentReadiness summary, and the tool's useWhen bullets. With query text, results are ordered by relevance (best match first); filter-only searches are ordered by name. There is no pagination — narrow with filters when more than 10 match. On no match, returns a "no tools found" message. Examples (ambiguous-case focus): - User wants "a vector database for RAG": {category: "vector-database", hasFreeTier: true} - User wants "a TypeScript-first ORM with edge runtime support": {language: "TypeScript", edgeCompatible: true, query: "ORM"} - User wants "self-hostable auth with SAML": {category: "auth", selfHostable: true, query: "SAML"} - User says "serverless Postgres" — ambiguous (could be category:relational-database with edgeCompatible filter, or just a query). Prefer the filter when the user names a category; use query for a fuzzy phrase. - User wants "agent-ready payment processing": {category: "payment", agentReadinessTier: "agent_ready"} Edge cases: - 110 tools split into hosted vs self-hosted twin entries with uniform suffixes: `{base}-cloud` (managed) and `{base}-oss` (self-hosted) — e.g. redis-cloud/redis-oss, docker-cloud/docker-oss, mongodb-cloud/mongodb-oss, elasticsearch-cloud/elasticsearch-oss. Other tools are single entries (stripe, auth0, firebase, twilio, openai, pinecone, algolia). Filter by `selfHostable` or `artifactKind` to land on the right variant. - "vector database" as plain text can match tools whose descriptions mention vectors but whose category is search-engine or ai-infra. Use the `category` filter when the user wants a strict match. - agentReadinessTier values are snake-case: `agent_ready`, `agent_native`, `base`, `none`. Display labels (`Agent Ready`) will not match. `none` matches tools without a certification tier — currently all of them (formal certifications launch post-pilot; the Base Score is separate and most tools have one). - artifactKind has only two values: `open_source` and `managed_service`. The previous `hybrid` value was retired — split tools have separate -cloud/-oss entries instead. Risk: read-only, closed-world, idempotent — no state change possible.

  Connector

• search_tools

  Relaystation

  Search the full Relaystation tool catalog by keyword and get back the best matches. Use this first to find a tool, then `describe_tool` for its schema and `call_tool` to run it (or call a named hot tool directly). `query` is free text (e.g. "merge pdf", "csv to json", "send telegram"). `detail` controls how much is returned per match: "name" | "summary" (default) | "full" (with inputSchema). `limit` defaults to 5. FREE. Example: search_tools {query:"merge pdf", limit:5}

  Connector