Skip to main content
Glama

litmus

by io.github.polygraphso

Request a polygraph grade for an MCP server

request_grade
Idempotent

Record a grade request with polygraph.so. Recording is free; only real, plausibly-MCP targets are accepted. Grading starts once the request's one-time $1 USD fee is paid: payment.payUrl is the human/browser checkout (paid in $POLYGRAPH), and payment.x402Url is the agent rail, POST the same request body there with an x402-capable client. A bare POST to x402Url returns a 402 with the exact payment requirements; retry with an X-PAYMENT header. Asset is USDC on Base mainnet (eip155:8453). On the x402 rail settlement is deferred: the authorization is charged only once a grade lands, and a run the harness cannot complete voids it, so nothing is charged. Paying starts a 48h grading clock. The fee buys the run, never the grade. After paying, poll check_server with the same server_ref for the published result, or poll statusUrl for progress.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
server_refYesRegistry-prefixed server ref: npm/<name>, npm/@scope/<name>, pypi/<name>, or github/<owner>/<repo>, with an optional @version. Example: npm/@modelcontextprotocol/server-filesystem

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
demandYesHow many times this server has been requested.
statusYes
createdYesfalse if the server was already recorded.
paymentYesHow grading is paid for. The web checkout settles up front in $POLYGRAPH; the x402 rail takes an authorization that is charged only once a grade lands, and a run the harness cannot complete voids it, so nothing is charged. The fee buys the run, never the grade.
requestIdYesThe recorded request's id.
statusUrlYesPoll for grading progress (unpaid, grading, graded, failed); check_server also reflects the published result.
server_refYesThe server ref that was recorded.

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. First observed

TDQS

A4.4/5.0
Behavior5/5

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

Annotations provide basic flags; description adds rich behavioral context: deferred settlement, 48h clock, fee structure, and that the fee buys the run not the grade. No contradictions.

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?

Single dense paragraph, front-loaded with purpose. Every sentence adds value but could be restructured for readability. Effective but not maximally concise.

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?

Covers all necessary aspects: initiation, payment rails, polling alternatives, constraints, and outcomes. Output schema exists, so return values are not required. Fully adequate for agent use.

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?

One parameter (server_ref) with 100% schema coverage. The description repeats the schema's description verbatim, adding no new meaning. Baseline 3 maintained.

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 'Record a grade request with polygraph.so' using a specific verb and resource. It distinguishes from siblings (check_server, list_servers) by focusing on initiating the grade request process.

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?

Provides detailed guidance on payment and polling steps, and notes that only 'real, plausibly-MCP targets' are accepted. Lacks explicit when-not-to-use but context is sufficient.

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

All litmus toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.5/5.0
Disambiguation5/5

Each tool targets a distinct operation: checking a specific server's grade, listing servers with grades, and requesting a new grade. There is no overlap or ambiguity.

Naming Consistency5/5

All tools use a consistent verb_noun pattern with underscores (check_server, list_servers, request_grade), making predictions easy.

Tool Count5/5

With only 3 well-defined tools, the set is scoped perfectly for the server's purpose—graded server lookup, listing, and grade requesting—without extraneous or missing tools.

Completeness5/5

The tools cover the full lifecycle: checking a grade, listing available grades, and requesting a new grade. No obvious gaps are present for the domain.

Resources