"A tool for interpreting Python code" matching MCP tools:

• 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

• list_reference_data

  My App Store Ranking

  The enum values every other tool accepts. Call this before guessing a country code or category id: invalid parameters fail, and failed calls still count against the daily quota.

  Connector

• lookup_postal_code

  Postal Lookup MCP

  Resolve a postal/ZIP code to its place name(s), state/region, and coordinates. `country_code` is a 2-letter ISO code (US, GB, DE, ...); `postal_code` format varies by country (e.g. "90210" for the US, "SW1A 1AA" style outward codes for the UK). Use for "what city is ZIP 90210 in", "where is postal code X in country Y", or any question that needs a place name/region/lat-lon from a postal code -- not for the reverse (place name to postal code) or for full street address lookup. Some postal codes span multiple places, in which case all of them are returned. Returns an error dict (never raises) if the code isn't recognized for that country.

  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

• search_award_availability

  AwardSecrets Award Availability

  Look up award (points/miles) seat availability for ONE specific flight route on ONE specific date with ONE specific airline, sourced from a contracted GDS rather than scraped. Returns the flights found with cabin and seat count. IMPORTANT — this tool is strictly literal. Every argument takes a single concrete value: • origin / destination: exactly one 3-letter IATA airport code each. Not a city, not a list, not a region. • airline: exactly one 2-letter IATA carrier code (e.g. VS, CX, NH). Not an alliance and not a loyalty programme. • date: exactly one date, YYYY-MM-DD. Not a range and not a month. To cover several airports, airlines or dates, CALL THIS TOOL ONCE PER COMBINATION and combine the results yourself. Award space is scarce and volatile, so an empty result for one date says nothing about another — checking several dates is normal and expected. Interpreting the result: • seats is an availability indicator, not a guaranteed bookable count, and not a reservation. Low counts are the more precise signal; treat higher ones as less certain. Do not present any count as a firm number of seats a user can book. • cabin is one of business, first, economy or premium_economy. • An empty result means no availability was surfaced for that exact combination at that moment; it is not proof that the route never has space. • Availability changes fast. Treat every result as a point-in-time observation, not a reservation. If the call is declined for want of an API key, say so plainly and point the user at https://awardsecrets.com/api.html — access is in limited release and keys are issued individually. Do not invent availability, and do not substitute a guess for a result you could not retrieve.

  Connector

• get_profile

  DevMatch - AI Recruiting & Mission-Aligned Engineer Discovery

  Fetch one contributor's profile card for a GitHub handle not already returned by find_candidates — e.g. the user names a specific person, references an external handle, or wants verification before outreach. find_candidates already returns full inline profiles; use get_profile only for handles outside those results or when the user asks for deeper detail. Returns structuredContent (view=profile). Agents: consume structuredContent only. IMPORTANT — interpreting recent_activities: indexed GitHub activity in the current ingestion window (2025–2026), up to ~20 events per recent project. NOT a complete career history. Empty or older activity does not mean inactive.

  Connector

• set_param

  kernelcad

  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).

  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

• resolve_product_code

  EU Trade Explorer

  Resolve a free-text query or CN code(s) into validated product code(s) with descriptions -- the recommended first step before using a code as `product` in any other tool's `query`. Saves the search -> validate -> (optional) subtree round-trip: a bare keyword runs a search, a single code (or comma-separated list) is validated and described directly. Tip: Comext/CN nomenclature is frequently coarser than a colloquial product name (e.g. there is no code for "glass jars" alone -- only heading 7010, which bundles jars with bottles, flasks and closures). Check `has_subcodes` and, if useful, set `include_children=true` to see whether a finer sub-code is actually a better match before committing to one code for a whole report.

  Connector

• list_boundary_type_codes

  Boundr

  Returns every valid UK boundary type code mapped to its human-readable label. Call this before using any tool that accepts a `boundary_type` or `boundary_types` argument so you know which codes are legal. Passing an unlisted code to another tool raises a ValueError. Boundary type codes are stable Ordnance Survey identifiers. Common ones: - "CTY" → County - "LBO" → London Borough - "UTA" → Unitary Authority - "MTD" → Metropolitan District - "DIS" → District - "DIW" → District Ward - "CCTY" → Ceremonial County - "HCTY" → Historic County - "WMC" → Westminster Parliamentary Constituency - "GLC" → Greater London Constituency - "SWC" → Scotland/Wales Constituency - "PAR" → Parish - "CED" → County Electoral Division Returns: Dict mapping code → label for all supported boundary types, e.g. {"CTY": "County", "LBO": "London Borough", ...}

  Connector

• string_proteins_for_term

  STRING Database MCP Server

  Retrieve proteins annotated with a functional term or descriptive text in a single species. You can query for tissues, compartments, diseases, processes, pathways, and domains. IMPORTANT: For cross-species comparisons, run this tool separately for each species. Select relevant model organisms to search or ask user to provide the selection. The results reflect annotation depth within each category; use caution when interpreting. If no results are found, try simplifying the query. For tissue queries, follow BRENDA tissue nomenclature and omit the word "tissue" (e.g. use "skin" instead of "skin tissue"). Output fields: - category: Source database of the matched functional term (e.g. GO, KEGG, Reactome, Pfam, InterPro). - term: Exact identifier for the functional term. - description: The free text description of the term. - proteinCount: Number of proteins annotated with that term - preferredNames: Full protein-name list when `detail_for_term` is set - stringIds: STRING protein identifiers when returned - preferredNames_omitted: True when a row omits the protein-name list - stringIds_omitted: True when STRING identifiers are omitted

  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

• 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

• get_access_pattern

  dynamical.org Weather & Climate Catalog

  Get the storage URI and working code for opening a dynamical.org dataset's data. dynamical.org publishes a Python package, `dynamical-catalog`, that reads the STAC catalog itself to resolve and open a dataset -- it's the recommended access pattern because it can't go stale even if the underlying storage format or location changes. This tool also returns the dataset's low-level storage details (from the STAC asset, fetched live) and a lower-level xarray/fsspec snippet for callers who need direct access instead of the wrapper package. Args: collection_id: A STAC collection id, e.g. "noaa-gfs-forecast". Use search_catalog to discover ids. Returns: A dict with the recommended `dynamical_catalog.open(...)` snippet, a `worked_example` pulled from the collection's own STAC metadata when one is published, the raw asset URI/type/storage options, and a generated low-level open snippet (icechunk/zarr/geoparquet, chosen from the asset's declared type). Raises ValueError (listing valid ids) if collection_id is unknown.

  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

• atc_lookup

  Medical Terminologies MCP

  Look up an ATC code at level 1-4 to get its name and hierarchy level. Use this tool to: - Resolve an ATC code (e.g., "A10BA") to its class name ("Biguanides") - Confirm a code exists in the current ATC index - Identify the level (anatomical / therapeutic / pharmacological / chemical) Accepts codes 1-5 characters long: "A" (anatomical), "A10" (therapeutic), "A10B" (pharmacological), "A10BA" (chemical). Substance-level codes (7 chars, e.g., "A10BA02") are not exposed by this endpoint — use atc_classify with the drug name to retrieve the substance code.

  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