Skip to main content
Glama
jkanselaar

Python Code Validator

Execute Python

execute_python
Idempotent

Execute Python code in a sandboxed container to verify it runs and produces the expected output, exposing runtime errors and doctest mismatches that static analysis misses.

Instructions

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. 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.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
codeYesThe source to check, as a whole file where possible: diagnostics carry the line and column of the text you send, and a fragment hides the imports and definitions the type check needs. A deployment may accept fewer bytes than the 200000 here.
optionsNoTuning knobs. Most of them only take effect in the mode that does the corresponding work; see each field.
languageNoThe language of the code. A service that does not handle it refuses the request rather than guessing; the enum is shared across services, so it lists more than any one of them accepts.python

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
metaYes
fixesNo
scoreYes
validYes
runtimeNo
securityNo
fixed_codeNo
transpiledNo
diagnosticsNo
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description discloses critical side effects ('do not submit code you do not want executed'), sandbox constraints (no network, read-only filesystem, killed at timeout), auth requirements (paid key, HTTP 402 without one, credit cost), the fact that the repaired code is what runs, and data retention ('code and its verdict are retained'). This goes far beyond the annotations and gives the agent a complete safety picture.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

While lengthy, the description is exceptionally well-structured with clear sections (Auth:, Arguments:, Returns:), front-loads the core action, and every sentence carries operational detail. There is no fluff or redundancy; the length is justified by the tool's complexity.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description provides a complete contract: side effects, auth, cost, error codes, return field summary, repair/execute behavior, and data retention. It references the output schema for full return details, so it does not need to enumerate every field, making it appropriately complete for the tool's complexity.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Although the schema already has 100% coverage, the description adds substantial operational meaning: byte size limits with specific HTTP errors for code, the strict language requirement of 'python', the deployment cap on timeout_s versus the schema max, the purpose and effect of expected_output and examples, and the null semantics of fixed_code. This is value neither the schema nor annotations provide.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description immediately states the core action: 'RUNS the code in a throwaway container' and frames it as 'Everything repair does, and then...', giving a specific verb and resource. It also explicitly distinguishes itself from sibling tools by naming validate_python and repair_python as alternatives that do not execute code.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly tells the agent when to use this tool ('Use it when you need proof that the code runs, or that it does what it says') and clearly names alternatives with their non-executing nature. It also provides detailed usage guidance for options like expected_output and examples, specifying when to send them.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/jkanselaar/python-code-validator'

If you have feedback or need assistance with the MCP directory API, please join our Discord server