Skip to main content
Glama

verify

Server Details

Runs your code against a contract; returns HELD or BROKE at the exact input. Deterministic.

Status
Healthy
Last Tested
Transport
Streamable HTTP
URL

Glama MCP Gateway

Connect through Glama MCP Gateway for full control over tool access and complete visibility into every call.

MCP client
Glama
MCP server

Full call logging

Every tool call is logged with complete inputs and outputs, so you can debug issues and audit what your agents are doing.

Tool access control

Enable or disable individual tools per connector, so you decide what your agents can and cannot do.

Managed credentials

Glama handles OAuth flows, token storage, and automatic rotation, so credentials never expire on your clients.

Usage analytics

See which tools your agents call, how often, and when, so you can understand usage patterns and catch anomalies.

100% free. Your data is private.
Tool DescriptionsA

Average 4.5/5 across 2 of 2 tools scored.

Server CoherenceA
Disambiguation5/5

The two tools have clearly distinct purposes: one initiates a verification job, the other polls for its result. There is no overlap or ambiguity.

Naming Consistency4/5

Both tools use lowercase with underscores, but the first is a single word while the second follows a verb_noun pattern. The inconsistency is minor and does not hinder understanding.

Tool Count5/5

With only two tools, the server is well-scoped for its purpose: submitting verification jobs and checking their status. No extraneous tools.

Completeness5/5

The tools cover the entire workflow: submit (verify) and poll (verify_status). No missing operations, as the domain is ephemeral and does not require CRUD.

Available Tools

2 tools
verifyAInspect

Runs your code against a contract and returns HELD or BROKE at the exact input, deterministic and rerunnable. Executes JavaScript (Node) or Python 3 in an ephemeral sandbox that is discarded after the run; nothing is stored. Provide the code plus either a contract (fn + call/expected examples, e.g. lifted from your failing test) for a BROKE-capable verdict, or an assumption in plain words for a FINDINGS read. Verdicts: HELD (the code satisfies the contract), BROKE (the exact input where it does not, with a proof you rerun yourself), FINDINGS (a stated property strained under a generated input, returned for you to check), or DROP (not a deterministic checkable claim). It checks the code against the contract you give; it does not judge whether the contract is right. BROKE fires only from a contract you provide, and correct code is never told it is broken. Deterministic code and math only. Call it when a fix passes your own check but the target test still fails, or when the same failure repeats unchanged across edits. Paid per call over x402 on Base, 1 USDC, no account; if no verdict is produced, the payment is refunded on-chain.

ParametersJSON Schema
NameRequiredDescriptionDefault
codeYesThe function source under test. 16000 char max.
contractNoProvide a {call, expected} contract for a BROKE-capable verdict. BROKE fires only from a contract you provide.
assumptionNoA claim about the code in plain words, for a FINDINGS read (never BROKE). 4000 char max.
Behavior5/5

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

With no annotations, the description fully covers behavior: ephemeral sandbox, nothing stored, deterministic and rerunnable, paid per call on Base with 1 USDC, refund if no verdict. It also states what the tool does not do (judge contract correctness).

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

Conciseness4/5

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

The description is somewhat lengthy but well-structured, with the core action front-loaded. It covers verdicts, usage, payment, and environment without redundancy. A slight trim could improve conciseness, but every sentence is informative.

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?

Given the lack of output schema, the description thoroughly explains all possible verdicts (HELD, BROKE, FINDINGS, DROP) and conditions. It also covers parameters, payment details, sandboxing, and determinism, making it self-contained for agent understanding.

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 schema coverage is 100%, the description adds significant meaning: it explains that 'contract' is for BROKE-capable verdicts, 'assumption' for FINDINGS, and details the contract structure (fn, examples). This goes beyond the schema's basic descriptions.

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 clearly states the tool runs code against a contract and returns verdicts like HELD, BROKE, FINDINGS, or DROP. It specifies the verb (runs, returns) and resource (code against contract), and distinguishes itself from the sibling 'verify_status' by focusing on contract-based verification.

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 provides explicit usage scenarios: call when a fix passes own check but target test fails, or when same failure repeats. It advises against non-deterministic code and explains when to use contract vs assumption. It also covers payment and refund conditions.

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

verify_statusAInspect

Poll a verify job for its verdict. Pass the jobId the verify tool returned. Returns the status and, once complete, the verdict: HELD, BROKE (with the counterexample), FINDINGS, or DROP.

ParametersJSON Schema
NameRequiredDescriptionDefault
jobIdYesThe jobId returned by the verify tool.
Behavior3/5

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

No annotations provided, so description must cover behavioral traits. It lists possible verdicts and indicates async nature (returns status, then final verdict). However, does not describe polling semantics, error handling, or timeouts.

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?

Concise two sentences, front-loaded with purpose. Every sentence adds value.

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

Completeness4/5

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

Given simplicity of the tool (one param, no output schema), description adequately explains return values. Could mention retry logic but not essential.

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

Parameters3/5

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

Schema provides 100% coverage of jobId description. Description only repeats that it is the jobId from verify, adding no new semantic information.

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?

Clearly states it polls a verify job and returns verdict. Distinguishes from sibling 'verify' by indicating it takes a jobId from that tool.

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

Usage Guidelines4/5

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

Explicitly says to pass the jobId from verify tool, guiding correct usage. Could add guidance on polling behavior but sufficient for single-sentence instruction.

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

Discussions

No comments yet. Be the first to start the discussion!

Try in Browser

Your Connectors

Sign in to create a connector for this server.

Resources