"Evaluating Mistral Small 27B for function calling and replacing Claude 3.7 in Roocode" matching MCP tools:

• llm_generateA

  IA-QA — 130+ QA & Dev Tools for AI AgentsB

  Generate text using open-source LLM models hosted on Groq (ultra-fast) or HuggingFace Inference (serverless). No API key required — the server provides its own keys. Supported models: Qwen3 32B, Gemma 4 27B, Gemma 3 27B, Llama 3.3 70B, Llama 4 Scout, DeepSeek R1, Mistral Small 24B, and more. Use list_llm_models to see the full catalog. Rate-limited to prevent abuse.

  ConnectorNo auth

• set_paramA

  kernelcadA

  Use this when you need to edit a param() default value in a kernelCAD script. Returns the modified code as text plus diagnostics from re-evaluating the result. Caller persists the new code via standard file-write tools (this tool has no side effects).

  ConnectorNo auth

• revoke_api_keyA

  FlexYield — blockchain RPC gatewayA

  Revoke one API key of your account by id; calls with that key stop working immediately and the key cannot be restored. Use it when a key leaked or a service is retired; ids come from list_api_keys. Not for pausing a key (set its budget to a small cap with configure_key instead) and not for the key you are calling with unless you hold another. Returns JSON: id, name, revoked_at. Idempotent. Needs your API key.

  Connector

  Destructive

  No auth

• invoke_functionA

  wawesomeA

  Runs a deployed Function once, without waiting for a Schedule. It fires a method that is not a GET, sends a request body, and reaches a Function that is not on its public address. It answers with the invocation_id the run will run under, before there is anything to read by it: once the run has been through the worker, 'get_invocation' answers how it went and 'read_invocation_logs' what it printed. Nothing the Function served comes back here; 'fetch_function' answers what a path serves. One run at a time per Function; a second while one is in flight is refused.

  Connector

  Destructive

  OAuth

• revoke_api_keyA

  FlexYield — blockchain RPC gatewayA

  Revoke one API key of your account by id; calls with that key stop working immediately and the key cannot be restored. Use it when a key leaked or a service is retired; ids come from list_api_keys. Not for pausing a key (set its budget to a small cap with configure_key instead) and not for the key you are calling with unless you hold another. Returns JSON: id, name, revoked_at. Idempotent. Needs your API key.

  Connector

  Destructive

  No auth

• run_scriptA

  CrevioA

  Run JavaScript on the account's computer with bun — no agent turn — and wait for its result. `tools.<namespace>.<function>(args)` calls anything list_integration_tools shows (every call returns its result and throws on failure; top-level await works), and the script's last expression is its result. Chain calls and transform data in one run, e.g. `const { data } = await tools.crevioApi.listOrders({ status: "succeeded" }); data.length`. Runs as you, and only for account admins. If the wait ends first the reply has wait_timed_out: true and the run id: continue with wait_for_script_run — calling run_script again runs it twice unless you reuse the idempotency_key. Run ids do not expire, and only the user who started a run can read it. At most 4 runs in flight per user.

  Connector

  Destructive

  OAuth

• run_scriptA

  CrevioA

  Run JavaScript on the account's computer with bun — no agent turn — and wait for its result. `tools.<namespace>.<function>(args)` calls anything list_integration_tools shows (every call returns its result and throws on failure; top-level await works), and the script's last expression is its result. Chain calls and transform data in one run, e.g. `const { data } = await tools.crevioApi.listOrders({ status: "succeeded" }); data.length`. Runs as you, and only for account admins. If the wait ends first the reply has wait_timed_out: true and the run id: continue with wait_for_script_run — calling run_script again runs it twice unless you reuse the idempotency_key. Run ids do not expire, and only the user who started a run can read it. At most 4 runs in flight per user.

  Connector

  Destructive

  OAuth

• editA

  spacesheepA

  Update an existing space by replacing exact strings in its files — the preferred way to make SMALL changes to a space that already exists. You send only the snippets that change instead of the whole document, so a small fix costs a few hundred bytes rather than re-transmitting 50KB of HTML. Creates a new version exactly like `deploy`, so previous versions are kept and the space's URL, slug, access and org are untouched. Works on a space you own or one shared with you as an editor ('Can edit'); a worker space only its owner can change. Each edit's `old_string` must appear EXACTLY ONCE in the file unless `replace_all` is set — include surrounding context to disambiguate. For large changes to a file you have on local disk, prefer stage_begin + `deploy` with staged_sha (bytes travel via curl); use `deploy` when creating a space or adding/removing files.

  ConnectorOAuth

• resolve_topicA

  Pine ScriptA

  USE WHEN looking up an exact Pine Script API term or known concept keyword. Returns the best-matching doc paths with matched keywords and a retrieval suggestion (get_doc or list_sections + get_section). AFTER calling this tool, follow the suggestion: call get_doc() for small files or list_sections() + get_section() for large files. For natural language questions use search_docs() instead. Data sourced from bundled TOPIC_MAP and doc file content scan.

  ConnectorNo auth

• get_platform_statsA

  mcp-archimedesA

  Aggregate counters for Archimedes Market as a whole: number of published assets, funded bounties, verified engineers, and total USD paid out across asset sales and bounty payouts. Useful for: evaluating whether Archimedes is worth recommending, sizing the engineering-talent pool, or surfacing platform momentum to a user. Counters are cached upstream (60s).

  ConnectorNo auth

• start_investigationA

  FixterA

  Claim a Fixter investigation for the calling user and fetch its full transcript. Accepts the investigation's UUID or its public slug (e.g. 'happy-otter-42'). This CLAIMS the investigation (records the caller as claimant) — only call it when the user intends to work on the investigation; use get_investigation_brief for read-only access. Returns JSON: id, publicSlug, headline, flow, channelId, threadTs, createdAt, claimedBy, sessionEntries (the raw Claude Agent SDK transcript of the original investigation).

  ConnectorAPI key

• set_app_subdomainA

  Fine StructureB

  Set or clear the app platform subdomain - the '<subdomain>.<base domain>' host Fine Structure already serves the app on. Runs the same ownership, format, reserved-name and uniqueness checks as the Studio subdomain field because it calls the same model function. Replacing a subdomain takes effect immediately and creates NO redirect: the previous name stops resolving to this app and is released for anyone to claim. Pass an empty subdomain to clear it. For a domain the user owns, use add_custom_domain instead.

  Connector

  Destructive

  No auth

• get_programA

  AIm Workout JournalA

  Get the active training program with its day templates (planned blocks/supersets and per-exercise targets), or null if there is no active program. Program-planning data is in get_coaching_context(task='new_program'), draft validation in review_program_draft, and saving or replacing a program in import_document.

  ConnectorOAuth

• searchA

  ABS Data (observed)A

  Run JavaScript against the whole catalogue document — every table, its dimensions, coverage and small-dimension options — in an isolated sandbox with no network. Use it to answer questions the fixed verbs make awkward: 'which tables have both an SA2 geography and a quarterly frequency?', 'list every dimension name and how often it appears', 'find codelists whose labels mention rent'. Your code runs inside an async function with `catalogue` in scope; `return` a JSON-serialisable value; console.log output is captured. // The `catalogue` object available in search(): interface Catalogue { provenance: { runId: string; observedAt: string }; corpus: { tables: number; seriesConfirmed: number; seriesImpliedByMetadata: number; density: number }; tables: Record<string, { // keyed by table id, e.g. catalogue.tables.CPI id: string; name: string|null; description: string|null; seriesCount: number; frequencies: string[]; coverage: { from: string|null; to: string|null }; density: number|null; family: string|null; geography: string|null; topics: string[]; dimensions: { id: string; position: number; codelist: string|null; optionCount: number; literal: boolean }[]; }>; options: { literal: Record<string, Record<string, string|null>>; // codelist id -> { code: label } for small codelists (<=64 options) branded: Record<string, number>; // large codelists -> option count (use abs.searchOptions in execute) }; }

  ConnectorNo auth

• list_functionsA

  LexGO JobsA

  List LexGO job function names (lawyer, in-house counsel, paralegal, notary, …) for use as function_id filters. Names only; no SEO HTML. Prefer list_taxonomies for the full vocabulary.

  ConnectorNo auth

• check_serverA

  protogridA

  Probe a remote MCP server URL once, credential-free and without calling its tools, and get its quality checks and its readiness for the Claude and OpenAI directories. Pass `url` to start a check (waits up to 25 s for the result), or `id` to read one. Quota: a few checks per hour anonymously, more with an API key.

  ConnectorNo auth

• reshuffle_conceitsA

  weReciA

  Regenerate the collection's curated shelves ("conceits") — a fresh themed re-grouping of every entry, replacing the current shelves. BEFORE calling: confirm the user actually wants a reshuffle, and ask whether they'd like to give the curation a creative direction (a theme, mood, or organizing idea — e.g. "lean into late-summer produce"). Pass their answer as `guidance`, or omit it for a clean-slate shuffle. The run takes about a minute in the background; call list_conceits afterwards to see the new shelves.

  ConnectorOAuth

• list_logsA

  AALYA

  Browse request and Function execution logs for a project — 'was it my engine or my Function code' debugging, with rich filtering. log_type='requests' returns one row per API request (status, latency split into engine vs. Function time, redacted payload). log_type='function_logs' returns one row per Function invocation within a request's chain (status, duration, its own error text in full, and its captured print() output). The two share a requestId — use get_request_trace to fetch both sides of one request in a single call. Filters: tenant_id, entity, http_method, and (function_logs only) function_id are exact-match and fast. At least one of those, an exact request_id, or a bounded created_after/created_before time range is required — an unfiltered, unbounded query is rejected, since `requests` rows never expire.

  ConnectorAPI key

• executeA

  Cheapest LLM APIA

  Run a JavaScript async function in an isolated sandbox, composing catalog_search, model_detail, offer_compare, benchmark_results, provider_list, and benchmark_list as catalog.* methods. Return a small JSON value. Example: async () => { const page = await catalog.catalog_search({query: 'claude', page_size: 5}); return page.data.models.map(m => ({slug: m.slug, prices: m.bestOffer?.prices})); }. No network, secrets, or database binding is exposed. Shared worldwide execution budgets: 100 per UTC minute and 5000 per UTC day. Limits: 30 executions per client per minute (IPv6 /64), 20 catalog calls and read units (offer_compare uses 5), at most two concurrent calls, 5 seconds wall time, 50ms sandbox CPU, 32KiB code, 64KiB JSON output. JavaScript only; no imports or TypeScript syntax. Use /mcp?mode=code for only search + execute.

  ConnectorNo auth

• red-flagsA

  Clairvoyance

  Scans code against 17 design smells (the book's 14 named Red Flags plus 3 process-stage signals) and produces a structured diagnostic report. Use when the user asks for a red flags or design smell scan, asks to check code against a checklist, is evaluating unfamiliar code, or asks open-endedly whether anything is off in a named or pasted file, class, or function, or asks you to look it over. Not for a specific bug, error, or failing test the user has already identified. Not for a plain diff or PR review before merge, or whether a PR maintains design trajectory (use code-evolution for both), or diagnosing why code feels complex (use complexity-recognition).

  ConnectorNo auth

• list_docsA

  Pine ScriptA

  USE WHEN discovering what Pine Script v6 documentation is available. Returns a categorised list of doc file paths with one-line descriptions. AFTER calling this tool, call get_doc(path) for small files or list_sections(path) then get_section(path, header) for large files (ta.md, strategy.md, collections.md, drawing.md, general.md). Data sourced from bundled Pine Script v6 documentation.

  ConnectorNo auth