ImmunoGraph MCP

predict_mhci

Read-onlyIdempotent

Retrieves MHC-I peptide-binding observations for specified class-I alleles and peptide lengths via a configured IEDB connector or allowed exact fixture, returning method and source provenance.

Instructions

Get MHC-I peptide-binding observations for supplied class-I alleles and peptide lengths through the configured IEDB connector or an allowed exact fixture. Use for class-I evidence, not MHC-II or B-cell evidence. LIVE_ONLY requires the live connector; results include method and source provenance, and unavailable sources return a structured failure.

Input Schema

Name	Required	Description	Default
`runId`	No	Caller-chosen identifier linking this call to one research run.	interactive-run
`alleles`	Yes	HLA allele identifiers relevant to the selected MHC class.
`methods`	No	Named predictor methods to run or replay; availability depends on configuration.
`sequence`	No	Protein amino-acid sequence without a FASTA header.
`proteinRef`	No	Stable protein reference or exact fixture key for this prediction.
`fallbackPolicy`	No	Allowed source order; LIVE_ONLY forbids cache and fixture substitution, FIXTURE_ONLY forbids live calls.	LIVE_THEN_CACHE_THEN_FIXTURE
`peptideLengths`	Yes	Peptide window lengths in amino-acid residues for the selected MHC class.

Output Schema

Name	Required	Description
`ok`	Yes	Whether execution completed successfully.
`data`	No	Tool-specific result fields on success.
`meta`	Yes	Run identifiers, timings, and input/output hashes.
`error`	No	Structured failure on unsuccessful execution.

Schema Changelog

Changes observed during successful MCP inspections.

Changed8 schema fields changedv0.2.1Oct 31, 2026

addedInput schema / properties / alleles / description

Added value: +"HLA allele identifiers relevant to the selected MHC class."

addedInput schema / properties / fallbackPolicy / description

Added value: +"Allowed source order; LIVE_ONLY forbids cache and fixture substitution, FIXTURE_ONLY forbids live calls."

addedInput schema / properties / methods / description

Added value: +"Named predictor methods to run or replay; availability depends on configuration."

addedInput schema / properties / peptideLengths / description

Added value: +"Peptide window lengths in amino-acid residues for the selected MHC class."

addedInput schema / properties / proteinRef / description

Added value: +"Stable protein reference or exact fixture key for this prediction."

addedInput schema / properties / runId / description

Added value: +"Caller-chosen identifier linking this call to one research run."

addedInput schema / properties / sequence / description

Added value: +"Protein amino-acid sequence without a FASTA header."

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "$schema": "https://json-schema.org/draft/2020-12/schema",
+  "additionalProperties": {},
+  "properties": {
+    "data": {
+      "additionalProperties": {},
+      "description": "Tool-specific result fields on success.",
+      "properties": {},
+      "type": "object"
+    },
+    "error": {
+      "additionalProperties": false,
+      "description": "Structured failure on unsuccessful execution.",
+      "properties": {
+        "category": {
+          "type": "string"
+        },
+        "code": {
+          "type": "string"
+        },
+        "details": {
+          "additionalProperties": {},
+          "properties": {},
+          "type": "object"
+        },
+        "message": {
+          "type": "string"
+        },
+        "retryable": {
+          "type": "boolean"
+        }
+      },
+      "required": [
+        "code",
+        "category",
+        "message",
+        "retryable"
+      ],
+      "type": "object"
+    },
+    "meta": {
+      "additionalProperties": {},
+      "description": "Run identifiers, timings, and input/output hashes.",
+      "properties": {
+        "completedAt": {
+          "type": "string"
+        },
+        "durationMs": {
+          "type": "number"
+        },
+        "inputHash": {
+          "type": "string"
+        },
+        "outputHash": {
+          "type": "string"
+        },
+        "requestId": {
+          "type": "string"
+        },
+        "runId": {
+          "type": "string"
+        },
+        "startedAt": {
+          "type": "string"
+        },
+        "toolName": {
+          "type": "string"
+        },
+        "toolVersion": {
+          "type": "string"
+        }
+      },
+      "required": [
+        "requestId",
+        "runId",
+        "toolName",
+        "toolVersion",
+        "startedAt",
+        "inputHash"
+      ],
+      "type": "object"
+    },
+    "ok": {
+      "description": "Whether execution completed successfully.",
+      "type": "boolean"
+    }
+  },
+  "required": [
+    "ok",
+    "meta"
+  ],
+  "type": "object"
+}

First observedv0.2.0Oct 31, 2026

TDQS

A4/5.0

Behavior4/5

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

Annotations already declare readOnlyHint and idempotentHint, and the description goes further by disclosing that LIVE_ONLY forbids fallback substitution, that results carry method and source provenance, and that unavailable sources yield a structured failure rather than an error. That is genuine added context about failure and sourcing behavior; only auth/quota details are missing.

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?

Three sentences, no filler, with the resource and scope front-loaded ahead of the exclusions. The final sentence is a run-on stacking three separate facts (LIVE_ONLY, provenance, structured failure) with semicolons, which is slightly dense but still readable.

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, so return-value shape need not be explained, and annotations cover the safety profile. What remains for the description to carry — scope, sibling exclusion, source-fallback constraints, and failure behavior — is all present, so an agent has what it needs to call this correctly.

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 description coverage is 100%, so every one of the seven parameters, including the fallbackPolicy enum values, is already documented in the schema. The description restates the LIVE_ONLY constraint already present in the fallbackPolicy field description but adds no new semantics for alleles, peptideLengths, methods, or proteinRef. Baseline 3 applies.

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?

States a concrete resource (MHC-I peptide-binding observations) scoped to class-I alleles and peptide lengths, and explicitly excludes MHC-II and B-cell evidence, which separates it from predict_mhcii and predict_bcell. The verb 'Get' sits in mild tension with the tool name 'predict', leaving slight ambiguity about whether it retrieves recorded observations or runs a predictor, which keeps it from a 5.

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?

'Use for class-I evidence, not MHC-II or B-cell evidence' gives an explicit exclusion and names the competing siblings, so routing between the three predict_* tools is unambiguous. It does not cover when to prefer this over upstream siblings like generate_candidate_peptides or how to choose among the five fallbackPolicy modes, so no 5.

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

Deploy Server