Skip to main content
Glama
809,935 tools. Updated 2026-11-20 03:16

"A server for executing Python code, with support for MCP" matching MCP tools:

  • Audits Python source code for forbidden syscalls (os, subprocess, socket, open, eval) inside an AST-governed WebAssembly sandbox with no host filesystem access. Use when executing LLM-generated Python snippets safely; for checking shell commands without executing code, use verify_agent_command_safety instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'python_script' ('timeout_profile' defaults to 'fast_1s'), supports '?demo=true' or MPP (250 sats), and returns HTTP 400 if invalid.
    ConnectorNo auth
  • 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. Or pay for this one call with no key at all: call it without one and the result carries x402 payment requirements ($0.01 in USD Coin on eip155:8453); sign them and repeat the call with the payment in _meta['x402/payment']. 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.
    ConnectorNo auth
  • Grant or revoke the AMZ Vault support team's READ-ONLY view of this account: action=grant lets support see what the user sees for 7 days (auto-expires, they can change nothing, and every view notifies the user); action=revoke turns it off immediately. This changes who can access the account, so it ALWAYS needs the user's explicit go-ahead — offer it only when support needs to see a problem first-hand (usually alongside an account_feedback thread).
    Connector
    Destructive
    OAuth
  • Send the account holder a code to link the card issuer Starts the one-time card issuer link: the card issuer sends a one-time code to the account holder. Then call `POST /verify-card-issuer-link` with the code they enter. **The account holder, never the agent, receives and enters the code.** Send your human to their own inbox (or phone) and have them type the code into your interface. Never try to read the account holder's email or messages yourself, and never ask for their email password or access. **Where the code goes.** An account with an email on file always gets the code at that email; `email` and `phone` are ignored for it. An account with no email (a wallet-only sign-in) must send exactly one of `email` or `phone` (E.164). The response names the destination masked, never in full. **Limits.** Codes last 10 minutes. At most 5 codes can be sent per account in any rolling hour (`429`, with `Retry-After`). Sending a new code replaces the previous one, which then stops working. **Prerequisite:** Laso identity verification (`403 kyc_required` otherwise, with a `kyc_url`). If the account is already linked, this answers `200` with `status: linked` and sends nothing, so calling it twice is safe. **This route is free.**
    ConnectorOAuth
  • Use only after works_public_eligibility returns eligible. Download that immutable public GitHub snapshot, run the selected pinned static contract without executing repository commands, and return a signed receipt. Return the report field verbatim and stop.
    ConnectorNo auth
  • Get a new API key for an existing Disco account. Sends a 6-digit verification code to the email address. Call discovery_login_verify with the code to receive a new API key. Use this when you need an API key for an account that already exists (e.g. the key was lost or this is a new agent session). Returns 404 if no account exists with this email — use discovery_signup instead. Args: email: Email address of the existing account.
    ConnectorNo auth

Matching MCP Servers

Matching MCP Connectors

  • Proves AI-generated Python does what you asked: lint, types, security, sandbox run, exact fixes.

  • Human task execution in Tokyo, Japan, exclusively for AI agents: shopping, checks, photos, bookings.

  • Get SSH connection info for a VPS/dedicated site. Only available for VPS/dedicated plans (not shared hosting). Requires: API key with read scope. Args: slug: Site identifier Returns: {"host": "184.107.x.x", "port": 22, "username": "admin", "ssh_command": "ssh admin@184.107.x.x"} Errors: NOT_FOUND: Unknown slug FORBIDDEN: Plan does not support SSH (shared plans)
    ConnectorNo auth
  • 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.
    ConnectorNo auth
  • Translate a plain-language question into a candidate SQL query using pattern-matching against the live schema (no AI model — simple questions only: counts, averages, filtered selects on a named table). Returns the SQL without executing it, with a confidence score; low confidence means the table was guessed. Review the statement and tables_used, then run it with scalix_db_query. For complex questions, read scalix_db_schema and write the SQL directly.
    ConnectorNo auth
  • Everything validation does, plus deterministic fixes: the corrected source comes back in fixed_code, and the original is kept whenever the fix cannot be proven safe. The code is still never run. Use it when validation failed and you want the fix rather than the diagnosis. Alternatives: validate_python when the diagnosis is enough; execute_python when the fix has to be proven to run. Auth: a key is required. This call needs a paid key and answers HTTP 402 without one. Credits are bought without an account, 3 per call: GET /v1/pricing says where to send the xDAI. Or pay for this one call with no key at all: call it without one and the result carries x402 payment requirements ($0.03 in USD Coin on eip155:8453); sign them and repeat the call with the payment in _meta['x402/payment']. 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. options.max_iterations (1..10, default 3) caps the fix/verify rounds: raise it for a file with several independent faults, leave it for a snippet. options.optimize (default false) additionally folds constants and drops dead code, and is only worth setting when you asked for a rewrite anyway. options.transpile_to (e.g. 'javascript') returns a translation of the *repaired* source in transpiled, not of what you sent. fixed_code is null when nothing could be proven safe to change, so treat null as 'no fix', not as an error. options.timeout_s, options.examples and options.expected_output do nothing here: nothing is run, so there is no clock, no stdout, and no way to check an example. 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.
    ConnectorNo auth
  • Everything repair does, and then RUNS the code in a throwaway container — no network, read-only filesystem, killed at options.timeout_s — reporting exit code, stdout and stderr. Any '>>>' examples in the code are run too, and one that does not print what it says is an error the other tools cannot see. This is a side effect: do not submit code you do not want executed. Use it when you need proof that the code runs, or that it does what it says. Alternatives: validate_python for the diagnosis and repair_python for the fix, neither of which runs anything. Auth: a key is required. This call needs a paid key and answers HTTP 402 without one. Credits are bought without an account, 10 per call: GET /v1/pricing says where to send the xDAI. Or pay for this one call with no key at all: call it without one and the result carries x402 payment requirements ($0.1 in USD Coin on eip155:8453); sign them and repeat the call with the payment in _meta['x402/payment']. 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. options.max_iterations (1..10, default 3) caps the fix/verify rounds: raise it for a file with several independent faults, leave it for a snippet. options.optimize (default false) additionally folds constants and drops dead code, and is only worth setting when you asked for a rewrite anyway. options.transpile_to (e.g. 'javascript') returns a translation of the *repaired* source in transpiled, not of what you sent. fixed_code is null when nothing could be proven safe to change, so treat null as 'no fix', not as an error. options.timeout_s (seconds, default 5) is the wall clock for the run; the schema allows up to 60 but this deployment caps it at 30 and refuses a larger value with 400. options.expected_output compares stdout byte for byte and adds an 'expected-output' diagnostic (valid=false) when it differs, which is how you ask for 'it did the right thing' rather than 'it ran'. options.examples is the same question for code with no output: pass what you asked for as doctest lines ('>>> total([1, 2])' then '3') or assertions ('assert total([1, 2]) == 3'), and each is run against the code -- one that does not hold is a 'python:example-mismatch' error, and repair looks for a single-token change that makes them all pass. Send it whenever you know what you asked for: without it, code that runs but returns the wrong answer looks perfect from here. The program that runs is the repaired one, so read fixed_code before you trust runtime.stdout, and it runs exactly once however many rounds the repair took. 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.
    ConnectorNo auth
  • Dry run: compute what a sync would import / export / remove for the active Space, without executing. Use before trigger_sync to see the blast radius. Honours the same campaign_ids hard scope and force as trigger_sync, and returns a planHash you can pass to trigger_sync (plan_hash) to execute exactly this plan or fail on drift. Scoped to the active Space — see set_active_space to switch, or pass space_id to override for this one call.
    ConnectorAPI key
  • Validates a Python automation script that runs OUTSIDE the game, on three axes: Python syntax (using the real interpreter), Minecraft commands embedded in the script (against the official command index), and the shape of the /connect WebSocket message envelope. For behavior pack scripts use validate_script instead — Python does not run inside a pack. The embedded command check is the most valuable one: a command written from memory can look syntactically fine and still do nothing in the game. Only strings starting with / are treated as commands. If syntax could not be checked, syntaxChecked is false in the result; ok:true alone does not mean the syntax is valid.
    ConnectorNo auth
  • List the postcoordination axes WHO allows for one ICD-11 stem code (MMS linearization, pinned release). Postcoordination means attaching extra detail to a stem code — severity, laterality, anatomy, causing agent, etc. — to build a composite (cluster) code. Use this tool to: - See which axes a stem code accepts before building a composite code - Check which axes are REQUIRED vs optional - See whether an axis takes one or several values, and how many values it offers Provide an ICD-11 `code` (e.g., "BA00"). Returns one entry per axis with `axis_name`, `required`, `allow_multiple` and `value_count` — the count of allowed values, not the values themselves. A code with no postcoordination, or one WHO does not know, returns an empty `axes` list (not an error), so check the code with icd11_lookup if the list is unexpectedly empty. When NOT to use: this does not build or validate a composite code, and it does not list the allowed values; to get a code from a disease name, use icd11_search.
    ConnectorNo auth
  • Read an existing booking by its ATA confirmation code returned by a successful booking or supplied by the traveler. Never invent a code. Requires a current signed ATA traveler assertion, a verified legacy MCP session, or an approved BOOKING_READ handoff with matching booking email and code. For stateless third-party clients, use start_traveler_handoff with action BOOKING_READ and confirmationCode, then poll get_traveler_handoff_status. Returns booked stay, prices, payments and cancellation terms. Cannot modify, cancel, pay, or create inventory holds. Never use a confirmation code as holdId in get_reservation_status.
    ConnectorNo auth
  • Use when the user asks to inspect, summarize, or visualize an attached TFLite, ONNX, GGUF, SafeTensors, Core ML, or ExecuTorch deployment artifact. Opens a browser-local analyzer, returns a hash-bound format-neutral Model IR table and static evidence summary, and provides deterministic document views without executing model code. Do not use for training checkpoints, measured latency, task accuracy, clinical validity, regulatory compliance, or actual runtime placement.
    ConnectorNo auth
  • Add 1 to 1,000 codes you ALREADY have — from a POS, a CRM or a printed batch — to a sweepstakes, with attributes shared by all of them. To have Sweeppea invent the codes for you, use generate_codes instead. Codes are up to 20 letters, digits, - or _; whitespace is stripped; they are matched exactly and case-sensitively. The response reports Duplicates and Invalid separately from Created — always tell the user those counts rather than claiming every code landed. Requires the Codes & Coupons module enabled on the account — on 403 "module not enabled", do NOT retry; tell the user to contact Sweeppea support.
    ConnectorNo auth
  • Confirm the email with the 6-digit code, or check whether the email link was clicked. Preferred: confirm_signup(account_id, code, signup_token). The first confirmation returns api_key; store it, it is shown once. Link clicked instead: call confirm_signup(account_id, signup_token) every 5 seconds, up to 10 minutes, until email_verified is true, then call create_api_key. A code allows 5 attempts and lasts 24 hours. For a new code, call resend_code(email).
    ConnectorAPI key
  • Join the waitlist for early access to the Synoptic trading terminal (beta) for the signed-in account. Sets terminalAccessRequested, which get_me reports; repeating the call changes nothing. Does not grant access, open a support ticket or place trades. Use request_feature for other product requests.
    ConnectorNo auth
  • List the packaging types (package_type codes) a shipment can declare, e.g. 4G = caja de cartón; the catalog is the same for every account. The user does not know these codes and values like 'package' are invalid, so never guess one: ask how the item is packed in plain words ('caja', 'sobre', 'tarima') and search it with `name`, or confirm a known code with `code`. Use list_consignment_notes instead for the carta porte code of what is inside, and list_products for the account's saved catalog items. Returns `data` (code and name per type) and pagination `meta`.
    ConnectorOAuth
  • List the companies in an industry, using the SEC's Standard Industrial Classification (SIC). Pass a SIC code (3-4 digits, e.g. "6200" for securities brokers and exchanges, "3571" for electronic computers, "7372" for prepackaged software) to get its companies: CIK, name, ticker, exchange, state of incorporation and fiscal year end, 100 per page, companies with a ticker first. Get a company's own code from get_company or search_companies (sic). A sector is often several codes: pass a range or a list ("2000-2099" for all food and beverages, "2833-2836" for drugs, "2080,2086"), and each company then carries its own code; codes lists the codes found with their titles and company counts. A ticker is not an exchange listing: OTC companies have tickers too, so for exchange-listed companies pass exchange="NYSE,Nasdaq". Every answer with a code also has by_exchange: how many of its companies are on each exchange (none = no exchange ticker), so one call says how a sector splits between NYSE, Nasdaq and OTC. With exchange and no industry you get every company listed there (e.g. exchange="NYSE"), by name, 100 per page, each with its SIC code and title, and by_sic: how many of them each SIC code has. With neither industry nor exchange you get the exchanges themselves: every name SEC's ticker file uses, with how many companies are on each. If you do not know the code, pass a word from the industry name instead ("software", "pharmaceutical", "bank", "oil") and you get the matching SIC codes with how many companies each has; then call again with the code you want. list_sic_codes shows the whole classification. SIC is the SEC's classification of the filer, assigned when it registers. It is not GICS or NAICS, individuals and most funds have none, and some codes are broad (e.g. 6770 "blank checks"). Args: industry: a SIC code like "6200", or a word to look up codes by ("software"); may be left out when exchange is given query: with a code: only companies whose name or ticker contains this page: with a code: page number, 100 companies per page (default 1) listed_only: with a code: only companies that have a ticker (default True; OTC included). Set False to include the many dormant, delisted and asset-backed entities that carry the same code. exchange: only companies listed on one of these, comma-separated, as SEC names them: NYSE, Nasdaq, OTC, CBOE, TXSE; without industry, every company listed there
    ConnectorNo auth