Skip to main content
Glama

research_access

Idempotent

Get the user a free HLA-Verify API key, instantly. HLA-Verify is free for anyone: the key comes back in this result (status issued, field key) with 1,000 calls/day, 250 typings per call and 60 requests/minute; the user sends it as the X-API-Key header (or connects this MCP server with it). Ask before calling: it stores the email address with the key, used for service notices only. The key is shown once: give it to the user straight away. One key per address; asking again returns already_issued and never the key (lost keys: hello@hlaverify.com). Disposable inboxes are refused. Verified labs that need more can set tier "lab" with institution and use_case to apply for the Lab tier (10,000 calls/day, 5,000 typings per call): that is reviewed, and an approved key is emailed.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "email": "<email>"
    },
    "name": "research_access"
  }
}

Input Schema

NameRequiredDescriptionDefault
tierNoOmit for a free key now. "lab" applies for the Lab tier instead (institution and use_case required).
emailYesThe user's email address. Stored with the key; service notices only.
sourceNoWhere the request came from, e.g. mcp (optional).
use_caseNoWhat the API would be used for (optional; required with tier lab, where the decision is made on it). No patient details.
institutionNoLab, hospital, university, registry or company (optional; required with tier lab).
expected_volumeNoRough call or typing volume, e.g. 'about 20,000 typings a month' (optional).

Output Schema

NameRequiredDescriptionDefault
okYesAlways true; a refused request comes back as an error result.
keyNoThe API key, only when status is issued. Give it to the user; it is not shown again.
tierNo
usageNo
issuedNo
limitsNo
statusYesissued: `key` holds a new free key, shown only this once. already_issued: this address already has a key (never shown again; lost keys: hello@hlaverify.com). recorded/already_recorded: a Lab-tier application (tier "lab") is on file. All are success; do not retry.
key_refNoThe key's first 8 characters.
messageYesWhat to tell the user.
releaseYesIPD-IMGT/HLA release every verdict was computed against.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed16 schema fields changed
    • changedInput schema / properties / email / description
      Previous value: -"The applicant's email address. The approval code is sent here."New value: +"The user's email address. Stored with the key; service notices only."
    • changedInput schema / properties / institution / description
      Previous value: -"University, hospital, institute or nonprofit the work is done at."New value: +"Lab, hospital, university, registry or company (optional; required with tier lab)."
    • changedInput schema / properties / source / description
      Previous value: -"Where the application came from, e.g. mcp (optional)."New value: +"Where the request came from, e.g. mcp (optional)."
    • addedInput schema / properties / tier
      Added value: +{
      +  "description": "Omit for a free key now. \"lab\" applies for the Lab tier instead (institution and use_case required).",
      +  "enum": [
      +    "lab"
      +  ],
      +  "type": "string"
      +}
    • changedInput schema / properties / use_case / description
      Previous value: -"What the research or teaching is, and what the API would be used for. This is what the decision is made on, so be specific. No patient details."New value: +"What the API would be used for (optional; required with tier lab, where the decision is made on it). No patient details."
    • changedInput schema / required
      Previous value: -[
      -  "email",
      -  "institution",
      -  "use_case"
      -]New value: +[
      +  "email"
      +]
    • addedOutput schema / properties / issued
      Added value: +{
      +  "type": [
      +    "string",
      +    "null"
      +  ]
      +}
    • addedOutput schema / properties / key
      Added value: +{
      +  "description": "The API key, only when status is issued. Give it to the user; it is not shown again.",
      +  "type": "string"
      +}
    • addedOutput schema / properties / key_ref
      Added value: +{
      +  "description": "The key's first 8 characters.",
      +  "type": [
      +    "string",
      +    "null"
      +  ]
      +}
    • addedOutput schema / properties / limits
      Added value: +{
      +  "properties": {
      +    "burst": {
      +      "type": "string"
      +    },
      +    "calls_per_day": {
      +      "type": "integer"
      +    },
      +    "typings_per_call": {
      +      "type": "integer"
      +    }
      +  },
      +  "type": "object"
      +}
    • changedOutput schema / properties / message / description
      Previous value: -"What to tell the user, including that approval is by hand and not instant."New value: +"What to tell the user."
    • changedOutput schema / properties / ok / description
      Previous value: -"Always true; a rejected application comes back as an error result."New value: +"Always true; a refused request comes back as an error result."
    • changedOutput schema / properties / status / description
      Previous value: -"already_recorded: this address already has an application on file. Both are success; do not retry."New value: +"issued: `key` holds a new free key, shown only this once. already_issued: this address already has a key (never shown again; lost keys: hello@hlaverify.com). recorded/already_recorded: a Lab-tier application (tier \"lab\") is on file. All are success; do not retry."
    • changedOutput schema / properties / status / enum
      Previous value: -[
      -  "recorded",
      -  "already_recorded"
      -]New value: +[
      +  "issued",
      +  "already_issued",
      +  "recorded",
      +  "already_recorded"
      +]
    • addedOutput schema / properties / tier
      Added value: +{
      +  "type": "string"
      +}
    • addedOutput schema / properties / usage
      Added value: +{
      +  "properties": {
      +    "curl": {
      +      "type": "string"
      +    },
      +    "docs": {
      +      "type": "string"
      +    },
      +    "header": {
      +      "type": "string"
      +    },
      +    "mcp": {
      +      "type": "string"
      +    },
      +    "mcp_config": {
      +      "type": "string"
      +    },
      +    "usage": {
      +      "type": "string"
      +    }
      +  },
      +  "type": "object"
      +}
  2. Added

TDQS

A4.5/5.0
Behavior5/5

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

Goes well beyond the annotations (readOnlyHint=false, openWorldHint=false, idempotentHint=true) by disclosing concrete limits (1,000 calls/day, 250 typings per call, 60 req/min), the storage/persistence side effect of the email, the show-once key handling, the disposable-inbox refusal, and the human-reviewed Lab tier flow. The 'asking again returns already_issued' behavior is consistent with idempotentHint=true, so there is no contradiction.

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 purpose and the rate limits are front-loaded, and nearly every clause carries an operational fact (limits, warning to ask first, one-key rule, lab path). The single dense paragraph stacks several distinct concerns, so light restructuring would improve scanability, but there is little true filler.

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?

An output schema exists, yet the description still names the key return fields (status issued, field key), and it covers the failure modes (already_issued, disposable inboxes, lost key) plus the escalation path. An agent has everything needed to call this correctly and to instruct the user on handling the secret.

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

Parameters4/5

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

Schema coverage is 100%, so the baseline is 3, but the description adds decision-relevant meaning the schema only partly carries: what tier "lab" actually triggers (a reviewed application whose key is emailed), the one-key-per-address rule tied to email, and the prohibition on patient details. Minor gap: expected_volume and source are never mentioned in the description.

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

Purpose4/5

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

Opening sentence states a specific verb and resource — issuing a free HLA-Verify API key — so the agent knows exactly what this does. It is distinguishable from the analysis siblings (check_typing, match_score, etc.), though it never explicitly contrasts with beta_signup, the one sibling that could plausibly be confused with it.

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?

Explicitly gates invocation with 'Ask before calling' because the call stores an email address, and defines the branch condition for the alternative path (set tier "lab" with institution and use_case for verified labs needing more). It also spells out the re-request and lost-key cases with the exact outcome ('already_issued and never the key') and a fallback contact.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.