"A tool or library for executing Python code" matching MCP tools:

• get_design_guidelines

  Marmo UI MCP

  MANDATORY FIRST CALL before writing any @marmoui/ui code in this session. Returns a step-by-step generation checklist (which tools to call, in what order), critical rules (no namespace sub-components, PageSection is self-closing, no Sidebar export), component patterns, and ICON LIBRARY RULES. Pass iconLibrary (default "phosphor"; also "material" | "lucide" | "tabler" | "heroicons" | "feather") to get that library's import source, icon name map, and weight/style mapping — and pass the SAME value to review_generated_code so it enforces it. Ask the user which icon library they want before writing UI code. Call topic="patterns" to get the generation checklist specifically.

  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

• find_examples

  Senzing

  Find working SOURCE CODE examples from 37 indexed Senzing GitHub repositories. REQUIRED: either `query` (string, for search) or `repo` with `file_path` or `list_files=true` — the call WILL FAIL without one. Three modes: (1) Search: pass `query` to find examples across all repos, (2) File listing: pass `repo` + `list_files=true`, (3) File retrieval: pass `repo` + `file_path`. Indexes source code (.py, .java, .cs, .rs) and READMEs — NOT build/data files. For sample data, use get_sample_data. Covers Python, Java, C#, Rust SDK patterns: initialization, ingestion, search, redo, configuration, message queues, REST APIs. Use max_lines to limit large files. Returns GitHub raw URLs for file retrieval.

  Connector

• validate_python

  Python Code Validator

  Check Python source without running it: parse, lint (ruff), type-check (mypy), AST security policy, credential scan. Safe on code you do not trust. Use it on every Python file you generated or edited, before writing it to disk. Alternatives: repair_python to get the corrected source instead of the diagnosis; execute_python to prove the code runs. Auth: a key is required. A free key covers this call, 25 per day, then HTTP 429; get one with POST /v1/keys. Credits are bought without an account, 1 per call: GET /v1/pricing says where to send the xDAI. Arguments: code: the whole file, 1..200000 bytes of UTF-8 measured after encoding (empty is refused with 400, larger with 413); a fragment is fine, but line and column numbers in the answer count from 1 in what you sent. language: must be 'python'; anything else is 400, and the field may be omitted. Of options only transpile_to (e.g. 'javascript', which returns a translated copy in transpiled) acts here; timeout_s, max_iterations, optimize, examples and expected_output need a pass that rewrites or runs the code, so send code alone. Ignored options are not refused, so a call that sets them looks like it worked; and code that does not parse is answered rather than refused: valid=false with the syntax error located, which is the point. Returns valid, score 0..1, diagnostics (rule, message, line, column), security findings, fixes, fixed_code and runtime; see outputSchema. The code and its verdict are retained to improve the service.

  Connector

• review_generated_code

  marmo-ui

  ⚠️ MANDATORY — call this on every piece of code you generate before returning it to the user. Validates TSX/JSX against real @marmoui/ui prop signatures and returns { valid, errors[], warnings[], suggestedFixes[], iconLibrary }. Catches: (1) unknown imports, (2) Tabs.List/Tabs.Trigger namespace misuse → auto-suggests TabsList/TabsTrigger fix, (3) PageSection used as wrapper (must be self-closing), (4) hallucinated props, (5) icons imported from the wrong icon library (pass iconLibrary — default "phosphor" — matching what you passed to get_design_guidelines; wrong-library icon imports are ERRORS). If valid=false, fix all errors and call this again. DO NOT return code with errors to the user.

  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

• glim_github_search

  glim.sh

  Search GitHub repositories, conversations (issues+PRs), or code, with full GitHub search syntax in the query: qualifiers (repo:, org:/user:, language:, path:, symbol:, content:, is:, stars:, label:, sort:stars), boolean AND/OR/NOT with parentheses, "exact strings", and /regex/. kind='repos': MINIMAL distinctive keywords - the project/library name only ('rtk', 'react query'); every extra word must ALL match and buries the canonical repo - filter with qualifiers, not prose. kind='code': ONE literal code pattern as it appears in files ('useState('), an "exact string", a /regex/, or symbol:name to find definitions, across 2.8M+ public repos; narrow with repo:/language:/path:. Not supported in code search: license:, enterprise:, is:vendored, is:generated. kind='conversations': returns compact previews - use glim_github_get for full content; sort: REPLACES relevance ranking (words match anywhere incl. comments), omit it for best matches. Set repo='owner/name' to scope to one repository (works with any kind; with repos it routes to conversations). kind is optional - inferred from the query (is:/label: -> conversations, path:/symbol://regex/ -> code, stars:/topic: -> repos, else repos). Returns compact text by default; pass format='json' for full structured data.

  Connector

• estimate_cost

  gisgp

  FREE — quote a paid tool's cost WITHOUT executing it or charging the wallet (call this before assess_property_hazard etc.). `units` = candidate/item count for per-unit-priced tools (currently only rank_hazard_safe_sites — pass the number of candidates you intend to submit); ignored (treated as 1) for every flat-priced tool. Returns JSON: {ok, tool_name, units, credits, eur_estimate} for credits-wallet tools; for assess_property_hazard_x402 (paid on-chain via x402, not the credits wallet) returns {ok, tool_name, units, payment, price_usd} instead; or {ok: false, error} for an unknown/free tool name.

  Connector

• examples.search

  AI Design Blueprint

  Search curated examples by free-text query, ranked by relevance, with optional filters: principle_ids (only examples covering those principles), difficulty (beginner/intermediate/advanced), library (e.g. 'langgraph', 'openai'). Returns each match's slug, title, summary, principle coverage, difficulty, library, and source-code link — slug is the handle examples.get hydrates. Default limit 5, capped server-side. Use this when the user describes a use case, technique, or library and wants matching examples; prefer examples.get when you already have the slug; prefer guides.search when the user wants a full walkthrough; prefer principles.search when the user wants doctrine guidance, not an implementation. Results may include first-party agentic patterns (entry_kind='pattern') carrying an explicit doctrine binding, see examples.get. Filter to one family with pattern_family, which implies patterns only. Patterns take a small relevance preference over generic examples when otherwise equally relevant; that preference never outranks a genuine failing-principle match, and a pattern whose only relation to a failing principle is 'depends' receives no such match at all.

  Connector

• kirk_bulk_howto

  Kirk — Unsupervised Structural Change Detection

  Return a self-contained stdlib Python client for scoring at ZERO per-call LLM tokens. Purpose: Hand the caller an HTTP consumer that runs locally so bulk scoring doesn't burn LLM tokens per book. Use when: You need to score more than ~200 books, or `kirk_score_book_batch` returned `batch_too_large`, or the caller is running an autonomous bulk workload that would otherwise pay per-tool-call LLM tokens for every book. Do not use when: You are running a one-off interactive call — a direct `kirk_score_book` invocation is simpler; don't route through the client for a single book. Capability class(es): Cost-steering / delivery-path tool. Hands the caller a runner that exercises the same C2 / C5 / C6 capabilities as the MCP scoring tools, but at zero per-call LLM token cost. Path fit: The returned client is an HTTP consumer of the same MCP endpoint. Production integrations run in-process under sealed-engine attestation — same binary sha as this endpoint. Contact Kavara for deployment options. Cost: 0 IU. Free tool. Once running locally, the returned client bills against the same tools it drives: single-book calls at 1 IU each, and batch calls at 1 IU per 50 books (minimum 1 IU per call). A full 500-book batch → 10 IU. No LLM tokens on top. Cost comparison (2.7M-book validation rerun via 500-book batches — ~5400 batches, 54000 IU billed either way): MCP via Sonnet 5: $1,968 LLM + $540 IU + ~15 days wall clock MCP via Haiku 4.5: $656 LLM + $540 IU + ~10 days Python client (this tool): $0 LLM + $540 IU + ~55 min Return structure: { "language": "python", "filename": "kirk_online_client.py", "requirements": str, "usage": str, "code": str (the client source, ~500 LOC), "example": str (2-line copy-paste demo) }

  Connector

• generate_wallet

  Blueprint Agentic Staking (Solentic)

  Returns runnable code that creates a Solana keypair. Solentic cannot generate the keypair for you and never sees the private key — generation must happen wherever you run code (the agent process, a code-interpreter tool, a Python/Node sandbox, the user's shell). The response includes the snippet ready to execute. After running it, fund the resulting publicKey and call the `stake` tool with {walletAddress, secretKey, amountSol} to stake in one call.

  Connector

• get_icon

  Supericons

  Retrieve one exact SVG icon using an exact ref returned by search_icons, recommend_icons, or preview_icons. Do not guess icon IDs. Use search_icons first if the user only described a concept. Returns SVG code, explicit public library labels, visual preview URL, and public semantic guidance for the exact icon.

  Connector

• render_diagram

  Diagrams MCP

  Render a mingrammer/diagrams Python snippet to PNG and return the image. The code must be a complete Python script using `from diagrams import ...` imports and a `with Diagram(...)` context manager block. Use search_nodes to verify node names and get correct import paths before writing code. Read the diagrams://reference/diagram, diagrams://reference/edge, and diagrams://reference/cluster resources for constructor options and usage examples. Args: code: Full Python code using the diagrams library. filename: Output filename without extension. format: Output format — ``"png"`` (default), ``"svg"``, or ``"pdf"``. download_link: If True, return a temporary download URL path (/images/{token}) that expires after 15 minutes; if False, return inline image bytes. Defaults to True (URL) — set ``DIAGRAMS_INLINE_DEFAULT=true`` on the server to flip the default. SVG/PDF and PNGs larger than the inline limit always use a download link.

  Connector

• examples.get

  AI Design Blueprint Doctrine

  Get one curated example by stable slug. Returns title, summary, source-code links, principle coverage (the principle slugs the example demonstrates), difficulty, library/framework, and implementation notes. Use this when you already have the slug from examples.search, a principles.get response, or a guide cross-link; prefer examples.search when filtering by topic / principle / difficulty / library; prefer guides.get when the caller wants a full walkthrough rather than a single reference example. Returns error_payload on unknown slug. Some entries are first-party agentic patterns (entry_kind='pattern') rather than upstream cookbook examples: those additionally return pattern_slug, pattern_family, when_to_use, doctrine_relations (each {principle_id, relation, note, code_ref} where relation is one of structural / default_gap / depends), prior_art, and doctrine_binding_basis. Every other row omits those seven keys.

  Connector

• start_phone_verification

  agentcard

  Send (or re-send) the user's one-time funding verification code (the provider verifies the phone on the user's Agentcard identity, valid 60 days). add_funds already sends this code automatically when verification is needed — call this tool only to RE-send when the code never arrived (any unexpired code still works; sends are rate-limited). Returns the masked destination (text or email) and whether a code was sent; if the phone is already verified it says so and you go straight to add_funds. After the user reads back the code, call verify_phone.

  Connector

• customer_tiering_get_prep_code

  Customer Intelligence & Segmentation

  STEP 1 of 3 for the cheap sandbox path. Returns stdlib-only Python as `prep_code` (compact) and `prep_code_display` (readable, same logic), plus `reduction_spec` in words. Next: run one of those scripts (or your own from the spec) on the local CSV in your sandbox, then call customer_tiering_score_stats with the printed JSON. If the host needs code review first, show prep_code_display and wait for the user to say run/continue — then continue; do not invent a pause on hosts that allow silent runs. Python → MCP across turns is valid (ChatGPT Instant multi-step regressions are a host issue; Thinking/Auto or the next user turn still works). Do not invent rankings. If any step fails, fall back to customer_tiering with raw rows. This remote MCP NEVER reads the file — do NOT pass uploaded/attached file objects or platform upload handles. Call with no path args (preferred), or sandbox_path_hint as a plain string like 'book.csv'. Prefer this over customer_tiering when you have >~200 rows and a sandbox.

  Connector

• examples.get

  AI Design Blueprint

  Get one curated example by stable slug. Returns title, summary, source-code links, principle coverage (the principle slugs the example demonstrates), difficulty, library/framework, and implementation notes. Use this when you already have the slug from examples.search, a principles.get response, or a guide cross-link; prefer examples.search when filtering by topic / principle / difficulty / library; prefer guides.get when the caller wants a full walkthrough rather than a single reference example. Returns error_payload on unknown slug. Some entries are first-party agentic patterns (entry_kind='pattern') rather than upstream cookbook examples: those additionally return pattern_slug, pattern_family, when_to_use, doctrine_relations (each {principle_id, relation, note, code_ref} where relation is one of structural / default_gap / depends), prior_art, and doctrine_binding_basis. Every other row omits those seven keys.

  Connector

• search_linkedin_ads

  Hermoso

  Structured LinkedIn Ad Library search by company name, keyword, or companyId — use for a targeted B2B pull; use research_ads for open-ended research. Returns compact JSON {advertiser, headline, description, cta, link, media, dates, impressions} per ad — LinkedIn is the one library exposing real impression counts. Spends ScrapeCreators credits (~1).

  Connector

• check_injection

  ContrastAPI

  Scan source code for injection vulnerabilities: SQL injection, command injection, path traversal via unsafe string concatenation/unsanitized input. Supports Python, JavaScript, TypeScript, Java, Go, Ruby, Shell, Bash. Use to detect input-handling bugs; for secrets use check_secrets. Companion code-security tools: check_secrets (hard-coded credential detection), check_dependencies (known-CVE vulnerability audit), check_headers (live HTTP security-header validation), scan_headers (live HTTP scan via domain). Free: 30/hr, Pro: 500/hr. Returns {total, by_severity, findings}. No data stored.

  Connector

• encode_template

  Guild Wars 1 Build Compiler

  Compile a build (professions, attributes, 8 skills by exact English name) into an official in-game template code. The build is validated first; on rule violations the errors are returned instead of a code. Unknown skill names return closest-match suggestions. IMPORTANT: template codes MUST come from this tool — never write or guess a code by hand, hand-written codes are invalid in-game. If unsure, verify any code with decode_template.

  Connector