"A sandbox environment to run Python code and install dependencies" matching MCP tools:

• run_code

  tariff.watch

  Execute code in a persistent sandbox interpreter and return output. Defaults to Python.

  Connector

• tfplan

  InsideOut (Riley)

  PREVIEW: Run terraform plan to preview infrastructure changes Runs a terraform plan for an InsideOut session without applying any changes. This lets the user review what will be created/changed/destroyed before committing. Returns job_id, plan_id, and project_id. Use tflogs to stream the plan output. After the plan completes, use tfdeploy with plan_id to apply the exact plan. SINGLE-FLIGHT: only one TF job per session at a time. If another job is already in flight, tfplan returns tf_job_conflict with the live job_id — attach with tfstatus/tflogs, or pass force_new=true to override. REQUIRES: session_id from convoopen response (format: sess_v2_...). OPTIONAL: sandbox (boolean, default false) — plans real generated Terraform. Set to true for cheap sandbox template (testing only). OPTIONAL: force_new (boolean, default false) - bypass the single-flight guard. Use only when the existing run is provably wedged. CREDENTIAL HANDLING: Same as tfdeploy - credentials must be configured first.

  Connector

• cyanheads_describe

  cyanheads-mcp-server

  Return the description and install snippets for a named tool or server. For tools: the description and the server it belongs to. For servers: local (stdio, via npx) install snippets for every published server, plus remote (HTTP) connection snippets when a hosted endpoint exists — for every supported client, or one client via the client parameter. Call cyanheads_search first to find valid names.

  Connector

• deploy_from_url

  vibedeploy

  Publish a website to a live URL from a public archive link. Point this at a tar(.gz) archive on github / gist / S3 and the server fetches and deploys it, no upload from your side. Server-side fetch of a tar(.gz) archive from a public HTTPS URL, then deploy its contents. Sidesteps the case where your code-execution sandbox can reach github / gist / S3 etc. but not mcp.vibedeploy.be's upload endpoint. Equivalent to begin_deploy → POST uploadUrl → commit_deploy in one call. Hostname allowlist enforced; see the archiveUrl description.

  Connector

• use

  Vaaya

  Execute a single call that `consult` handed you, and bill on success. Used for any external capability (image/video/audio generation, web search, scraping, email, document parsing, code sandbox, browser automation, embeddings, etc.). The server validates params against a registered schema and proxies to the upstream — you never pass URLs or API keys. Always get the exact (service, action, params, max_cost_cents) from `consult` first — don't guess them.

  Connector

• ateam_redeploy

  ateam-mcp

  Re-deploy skills WITHOUT changing any definitions. ⚠️ HEAVY OPERATION: regenerates MCP servers (Python code) for every skill, pushes each to A-Team Core, restarts connectors, and verifies tool discovery. Takes 30-120s depending on skill count. Use after connector restarts, Core hiccups, or stale state. For incremental changes, prefer ateam_patch (which updates + redeploys in one step).

  Connector

• get_payment_options

  headless-oracle

  Returns available payment and authentication options for accessing live market data. Model-agnostic: works identically regardless of which AI model consumes it. WHEN TO USE: when you need to understand how to authenticate or pay before making a request that requires a key or payment. Returns upgrade ladder: sandbox (200 calls free), x402 per-request ($0.001 USDC), x402 sandbox (10 credits for $0.001), credit packs ($5 = 1000 calls), builder subscription ($99/mo = 50K/day). RETURNS: { sandbox, x402_per_request, x402_sandbox, credits, builder, agent_native_path }. No authentication required. Always returns 200.

  Connector

• axint.compile

  Axint

  Compile TypeScript source (defineIntent() call) into native Swift App Intent code. Returns { swift, infoPlist?, entitlements? } as a string — no files written, no network requests. On validation failure, returns diagnostics (severity, AX error code, position, fix suggestion) instead of Swift. Use: use when TypeScript DSL source should become Swift; use validate for cheaper preflight only. Inputs: source is TypeScript DSL text; options add sandbox, format, plist, or entitlement proof without writing files. Effects: read-only generated Swift/diagnostics; writes no files and uses no network.

  Connector

• get_strategy_code

  quantifyme

  Get the actual Python code behind a community leaderboard strategy. Use after `browse_community`: pass an entry's `id` here to read its real `feature_engineering()` + `strategy_config()` source so the user can inspect or tweak it. To deploy it unchanged, pass the same id to `one_shot` as `community_id`. Read-only, no signup needed. Args: community_id: The `id` of a community entry (from `browse_community`). Returns: dict with: id, title, username, description, symbol, timeframe, metrics {total_ret, win_rate, profit_factor, n_trades, mdd, sharpe_strat}, and `code` (the full Python source). SHOW the code to the user, and offer to deploy it via one_shot(community_id=...) or tweak it first.

  Connector

• create_test_outbound_mail

  mailbox

  Create a sandbox outbound mail record without uploading a real document. The record is always test_mode=true, cost_cents=0, includes estimated_live_cost_cents and cost_breakdown, and queues a mail.submitted webhook. Published default pricing is $0.30/page B&W printing; color adds $0.40/page ($0.70/page total before handling and postage). FedEx and UPS estimates use the same configured origin and destination zone/region logic as production. Use with a sandbox key to rehearse outbound workflows before sending real physical mail.

  Connector

• rent-browser

  mcp-server

  [Auth Required + Active] Get credentials to rent a real Chrome browser. Install CLI: `pip install ceki-sdk` (Python) or `npm install -g @ceki/sdk` (Node). Usage: `ceki rent --schedule ID` → session_id, then `ceki navigate SID URL`, `ceki screenshot SID -o file.png`, `ceki stop SID`. Per-minute billing from AgentWallet. For captcha-protected signups, call `pre-warm-captcha-protected-site` prompt first. Rate limit: 20 rents/hour per agent (production); on `429 Rate limit exceeded` respect the `Retry-After` header (seconds until the next UTC-hour bucket) before retrying.

  Connector

• consult

  Vaaya

  Vaaya's consultant. Describe ANY external capability you or the user might want — generate an image/video, search or scrape the web, run code in a sandbox, send/receive email, enrich a contact — and it helps figure out the best way, teaching the user what Vaaya can do. It is CONVERSATIONAL and remembers prior turns. It returns: mode='converse' (a reply to RELAY to the user verbatim — questions, options, ideas; get the user's response and call consult again with it, so the conversation continues), mode='call' (an ordered list of calls to run via `use`, with a message explaining the preferred choice + alternatives + why; multi-step results may contain placeholders like '<from step 1: sandbox_id>' — run earlier steps first and substitute), or mode='unsupported'. Every reply includes `suggestions` (2-3 things to do next) — surface these to the user. AFTER you run a `call` result's calls via `use`, call consult ONE more time with a short note on the outcome (what was produced / any failures) — it returns result-aware, Vaaya-grounded next steps to offer the user (the `call` result's `after_running` field reminds you). Call consult whenever you hit a capability gap or the user wants to know what's possible. It does NOT execute or bill — you run returned calls via `use`. ALWAYS show the user consult's `message` and `suggestions` and let them steer.

  Connector

• verify

  verify

  An outside check on code, executed in a sealed sandbox. Call it before code crosses a consequence boundary: before you merge it, deploy it, publish it, settle a payout on it, or report it done. A self-audit verifies consistency, never completeness: a check written inside the frame that produced the code passes on the code's own assumptions. This is the check that is not you. Also call it when a fix passes your own check but the target still fails; that means your check shares the code's assumption and cannot see the error. INPUT: code (JavaScript/Node or Python 3 source, deterministic only) plus ONE of: contract {fn, examples:[{call,expected}]} (copy call and expected from the test or spec the consequence depends on), or assumption (plain-language claim, weaker read). It checks the code against the contract exactly as given. VERDICTS (synchronous): BROKE: the code violates your contract, with the exact input and a rerunnable proof; do not proceed. HELD: the code meets the contract you gave; proceed on that contract, and nothing more. FINDINGS: a stated property strains under a generated input; check it before proceeding. DROP: not deterministically checkable. PAYMENT: 0.10 USDC per call, x402 v2 on Base, no account. Every delivered verdict is charged, HELD and DROP included. If no verdict is produced, the payment authorization is cancelled and you are not charged.

  Connector

• get_altinn_migration_guidance

  mcp

  Use this to discover the Altinn 3 equivalent of an Altinn 2 service or role code. The 19 June 2026 Altinn 2 deprecation deadline has passed, so this now serves remediation for any integration still on Altinn 2 — not pre-deadline planning. Pass an Altinn 2 code in { altinn2_code } (alphanumeric, 1–10 characters, e.g. A0208) to resolve a single mapping, or omit it to retrieve the entire migration map. Every response also carries the deprecation status computed in Europe/Oslo — `deprecation_deadline` (the absolute 23:59:59 Oslo instant on 19 June 2026), `days_remaining` (whole Oslo calendar days, floored at 0 once the deadline passes — 0 now that it has, never negative), and `deadline_passed` (now `true`) — so an agent can sequence its migration work without doing the timezone math itself. Each map entry ships a `verified` flag: `true` means the mapping has been cross-checked against DigDir's authoritative documentation, `false` means it is a convenience reference only — gate any production migration action on `verified === true` and treat unverified entries as hints, not instructions. The underlying data is a deterministic static map (DigDir-sourced); no government system is contacted at call time, so the answer is stable and cache-friendly. Input: { altinn2_code? }. Failure modes the agent must handle: 404 not_found when a supplied code is not in the map (omit the code to see every known entry); VALIDATION_FAILED (INVALID_CODE) on a non-alphanumeric or over-length code. This tool has no sandbox mirror — under the sandbox bearer it returns SANDBOX_TOOL_UNAVAILABLE.

  Connector

• run_code

  coremodels

  Execute a JavaScript program that orchestrates this server's tools, and return only its result. Prefer this over many individual tool calls when a task needs several steps, looping, filtering, or combining data: intermediate results stay in the sandbox, so only what you return reaches the model. Inside the script: - listTools() -> [{name, summary}] discover available tools - getToolDoc(name) -> {name, description, parameters, required} inspect one tool's inputs - tools.<name>(args) -> parsed result call a tool (graphProjectId is injected automatically; do NOT pass it) - console.log(...) captured and returned alongside the result - return <value> JSON-serialized and returned Environment: sandboxed JavaScript, no network or filesystem, with limits on time, memory, statements and number of tool calls. Currently only read-only tools are callable from code.

  Connector

• axint.activate

  Axint

  Run a source-free compiler smoke test through the real Axint pipeline. Use immediately after installing or connecting Axint so the current agent proves it did more than start the MCP server. Use: call immediately after install or first MCP connection; use validate or run for project checks. Inputs: format changes rendering only; the smoke test has no project inputs. Effects: read-only built-in compiler smoke test; writes no files and uses no network.

  Connector

• analyze_record

  Senzing

  Get the Senzing JSON analyzer script to validate mapped data files client-side. REQUIRED: `workspace_dir` (writable directory, e.g. ~/sz-workspace) — the call WILL FAIL without it. The analyzer validates records against the Entity Specification, examines feature distribution, attribute coverage, and data quality. Returns a Python script (no dependencies) with instructions. No source data is sent to the server. Typical workspace_dir values: Linux `/tmp` or `~/sz-workspace`; macOS `~/sz-workspace`; sandboxed envs: explicit path under home (do NOT assume /tmp exists).

  Connector

• transcode_video

  Botverse

  Offload a video transcode to Botverse — encoding runs server-side so you can continue with other tasks. Returns a job_id immediately. Source must be ≤ 10 minutes and ≤ 5 GB. Poll get_job_status every 5 seconds until 'complete', then get_download_url. Wallet debited on completion. Requires get_upload_url first — if you are in a sandboxed environment where that upload POST is blocked, use transcode_from_url (public URL) or transcode_content (inline) instead; no upload needed. RELIABILITY & FALLBACK: Botverse returns structured errors with a message. A bare 'HTTP 500' or 'tool call failed' with no message body is the MCP connector / sandbox layer between your client and Botverse — NOT a Botverse outage (the service is up if get_wallet_balance succeeds). If MCP calls keep failing, do NOT write your own ffmpeg / transcription / document-conversion code as a workaround — that wastes tokens and reinvents what Botverse does. Instead, tell the user to run the equivalent Botverse CLI from their own (non-sandboxed) machine, e.g. `npx botverse transcribe <file> --to docx` (also `transcode` and `convert`), then retry the MCP call.

  Connector

• request_jet_confirmation

  Villiers Charter

  Submit a request for CONFIRMED live private jet pricing. Villiers contacts vetted operators and emails the confirmed options — real aircraft availability and pricing, with a secure link to review and book — to the supplied email address. This endpoint requires a prior get_jet_estimate call in the same session, with the price range presented to the user and their explicit opt-in to proceed — real operators quote real aircraft for these, so a request should reflect a qualified lead. Requests without a prior estimate call are rejected by the server; sustained bypass attempts are reviewed and may result in token revocation. Requires the user's email and a departure date. SANDBOX TESTING: to test your integration without ever creating a real trip or contacting a real operator, use email 'sandbox-test@mail.villiers.ai' with first_name 'Sandbox', last_name 'Test', phone '+1 555 0100', route LHR to NCE. This exact combination is detected server-side from the request body itself (not from any header), so it works from any agent framework or HTTP client — including ones that don't allow a custom User-Agent. The response will say 'Test request accepted (sandbox mode detected)'. For further testing guidance, email affiliates@mail.villiers.ai.

  Connector

• explain_compliance_error

  mcp

  Resolve a structured Apier compliance error code into a Norwegian-bokmål Explanation envelope sourced from the Apier Compliance Explainer (PR-049). The response carries a one-line summary, a 1–3 sentence why, an ordered list of fix_steps, an optional Apier / Altinn / Skatteetaten / Brønnøysund relevant documentation link, an optional Lovdata-style legal_basis citation when the error maps to a concrete regulatory provision, and an optional handover block (who / where / what / why) for errors a human must resolve (e.g. AUTH_INSUFFICIENT_ROLE, AUTH_NO_DELEGATION, SCOPE_MISSING). Errors agents can resolve themselves (VALIDATION_FAILED, RATE_LIMIT_EXCEEDED, NOT_FOUND, IDEMPOTENCY_KEY_MISMATCH, IDEMPOTENCY_IN_PROGRESS, UPSTREAM_UNAVAILABLE) ship `handover: null`. The full catalogue of supported error codes mirrors `EXPLAINER_ERROR_CODES` (40 codes today across auth, validation, scope, upstream, idempotency, action-execute, government, and reliability domains); pass any code an Apier endpoint returned in an error envelope. The optional `context` object carries placeholder values (org_number, role, scope, field, upstream_system) that the explainer interpolates into the bokmål text — missing values fall back to a Norwegian 'ukjent <noun>' rather than leaking placeholder syntax. Required scope: `read:rulebook`. For a company's live obligations rather than an error explanation, use get_company_obligations instead. No API key? Self-serve in the sandbox: authenticate tools/call with `Authorization: Bearer apier_sandbox_test_<suffix>` (ALWAYS append a unique random suffix, e.g. a fresh UUID, for session isolation) and this tool answers from deterministic synthetic fixtures with `_meta.is_sandbox: true` — use the reserved MOD-11-valid sandbox org numbers from GET /api/v1/sandbox/fixtures (e.g. 999660088).

  Connector