Skip to main content
Glama

Immersive Commons

by com.immersivecommons

Verify an IC agent token you did not mint (service)

ic_token_verify
Read-only

Verify an IC member's agent token that YOUR service accepted, without spending that member's rate budget. *** DO NOT VERIFY BY HTTP STATUS CODE. *** IC's agent surface returns HTTP 200 with an in-band error envelope for an INVALID or absent token (e.g. {ok:false, error_kind:'no_token'}) — it does NOT return 401. Any check of the form if (response.ok) tokenIsValid = true therefore ADMITS EVERY FORGERY and fails OPEN. That is true of this tool too: a forged token gets HTTP 200 here. Validity is the status field in the BODY and nothing else. READ status, WHICH IS THREE-VALUED: 'valid' | 'invalid' | 'indeterminate'. Do NOT branch on !valid — valid is null when status is 'indeterminate'. 'indeterminate' (rate_limited / backend_unavailable / internal_error) means WE could not answer; it is NOT a rejection, so a rate-limited but perfectly good member must not be refused on it. Retry with backoff, and NEVER write an indeterminate result into a positive cache — otherwise anyone can manufacture a 'valid' verdict by DoSing the verifier. SCOPE DISCLOSURE IS INTERSECTED with your own token's scopes — you learn only which of YOUR capabilities the subject also holds, and scopes_filtered tells you the list was narrowed; it is a floor on their capability, never the whole of it. status:'valid' means the token is live and unrevoked, NOT that the bearer string alone can act: if requires_signature is true the token also needs an RFC 9421 signature per request. Verification never bumps the subject's rate counter or last_used_at, and never echoes the token back — key any cache of your own on a hash, never the raw token. Args: { token }. Returns: { ok, status, valid, member_id?, member_name?, tier?, scopes?, scopes_filtered?, token_prefix?, requires_signature?, sandbox?, reason? }. reason is malformed|unknown|revoked|no_scopes when status='invalid', and rate_limited|backend_unavailable|internal_error when status='indeterminate'. Rate: 200 verifications per calling token per UTC day. Required scope: agent:token:verify (ft-member+).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
tokenYesThe agt_... token to verify. Never logged, never echoed back.

TDQS

A4.6/5.0
Behavior5/5

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

Beyond the readOnlyHint annotation, the description reveals critical behavioral traits: HTTP 200 with in-band error envelopes for invalid tokens, a three-valued status field, the failure-open nature of naive checks, scope-disclosure intersection, rate-budget non-consumption, no token echo, and required RFC 9421 signatures. This is far beyond the annotation and is essential for correct invocation.

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 long but densely packed with critical security warnings and operational guidance. It is front-loaded with the core purpose, then structured warnings in bold. Every sentence adds necessary value, though it could be slightly more concise. For a security-sensitive verification tool, the length is well justified.

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 complexity (three-valued status, scope intersection, signature requirement, no output schema), the description is exceptionally complete. It fully explains the return fields, reason codes, rate limits, required scope, and failure modes. It leaves no reasonable ambiguity about how to interpret the results or what actions to take.

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?

The input schema already provides 100% coverage for the single parameter 'token' with a clear description ('The agt_... token to verify. Never logged, never echoed back.'). The tool description mentions the token but adds only marginal context (e.g., keying cache on a hash), not substantially improving parameter understanding beyond the schema.

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 opens with a specific verb+resource: 'Verify an IC member's agent token that YOUR service accepted,' clearly distinguishing it from generic verification tools. It further emphasizes the key differentiator of not spending the member's rate budget. The title also clarifies it verifies tokens 'you did not mint,' uniquely positioning it among all sibling tools.

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 states when to use: to verify tokens your service accepted. It provides strong when-not guidance: 'DO NOT VERIFY BY HTTP STATUS CODE' and warns against treating 'indeterminate' as rejection. It also gives specific retry and caching instructions, effectively serving as usage policy, even though it doesn't name a specific alternative tool.

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

All Immersive Commons 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

A3.7/5.0
Disambiguation4/5

Most tools are clearly scoped to distinct actions (e.g., ic_hack_apply vs. ic_hack_register, ic_rooms_create vs. ic_rooms_join). A few pairs could confuse an agent: floor10_submit_highlight vs. floorcast_push both submit HighlightStories but to different queues, and ic_directory_search / ic_agent_directory_lookup / ic_admin_list_members overlap in searching members. Overall, the long descriptions help disambiguate, but the volume requires careful reading.

Naming Consistency3/5

The dominant pattern is ic_<domain>_<verb>_<object> (e.g., ic_admin_list_pending_events, ic_headsets_checkout), but there are notable deviations: floor10_* and floorcast_* prefixes break the ic_ convention, and a few tools use noun-style names (ic_health, ic_capabilities, ic_donations_total). Verb placement also varies (get_* vs *_get, e.g., ic_get_my_membership vs. ic_membership_set_profile). Still, most names are readable and predictable.

Tool Count1/5

175 tools is an extreme count for a single MCP server, far beyond the 50+ threshold that indicates an unwieldy surface. While the platform covers many domains (events, files, hackathon, headsets, prints, rooms, etc.), bundling everything into one server makes discovery and selection difficult. This would be better split into several narrowly-scoped servers.

Completeness4/5

The tool set covers nearly every lifecycle for each domain: CRUD for files/folders, full hackathon admissions and judging, headset lending with waivers and incidents, print farm submission and handoffs, and room coordination. Minor gaps exist: no delete for files/folders, no cancel for events, and some actions (like revoking a Z.ai key or tearing down a room) are explicitly left to human console use. Overall, the surface is remarkably comprehensive for the stated scope.

Resources