Immunograph Mcp

v1.0.0

A powerful MCP server built with NitroStack

Connection Setup

Add via Cursor Settings UI (Settings > Features > MCP > Add New MCP Server): 

{
  "mcpServers": {
    // your other mcp servers
    "immunograph-mcp": {
      "url": "https://immuno-gra-rohith-kumar-dhamagatla-amrita-university-coimbatore.app.nitrocloud.ai/mcp"
    }
  }
}

Connect remote tools directly via Claude's Web UI:

Add custom connector BETA
Connect Claude to your data and tools. Learn more about connectors or get started with pre-built ones.
Advanced settings
Only use connectors from developers you trust. Anthropic does not control which tools developers make available and cannot verify that they will work as intended or that they won't change.
Building an MCP server? Report issues and subscribe to updates here

Configure custom tools directly via ChatGPT's Web UI:

New App
Icon (optional)
PNG only. Best results at 256 x 256 px or larger. Max file size: 10 KB
Name
Description (optional)
Connection
Authentication
Custom MCP servers introduce risk. Learn more
OpenAI hasn't reviewed this MCP server. Attackers may attempt to steal your data or trick the model into taking unintended actions, including destroying data.
Read the guide

Add the following configuration block under mcpServers in your Antigravity configuration file (~/.gemini/config/mcp_config.json): 

{
  "mcpServers": {
    // your other mcp servers
    "immunograph-mcp": {
      "serverUrl": "https://immuno-gra-rohith-kumar-dhamagatla-amrita-university-coimbatore.app.nitrocloud.ai/mcp"
    }
  }
}

Add the following configuration block to your Codex configuration file (~/.codex/config.toml): 

[mcp_servers.immunograph-mcp]
url = "https://immuno-gra-rohith-kumar-dhamagatla-amrita-university-coimbatore.app.nitrocloud.ai/mcp"

Connect directly using the Server-Sent Events endpoint: 

https://immuno-gra-rohith-kumar-dhamagatla-amrita-university-coimbatore.app.nitrocloud.ai/mcp
Available Tools
validate_sequence

Validate and normalize one protein FASTA record.

generate_candidate_peptides

Generate stable one-based T-cell peptide windows.

predict_mhci

Resolve MHC-I predictions through configured live/cache/fixture connectors.

predict_mhcii

Resolve MHC-II predictions through configured live/cache/fixture connectors.

predict_bcell

Resolve B-cell evidence; GraphBepi is fixture-only in MVP v1.

predict_synthetic_binding

Generate deterministic offline demonstration binding values; never scientific predictions.

normalize_scores

Normalize registered raw scores with versioned transformations.

compute_consensus

Compute deterministic weighted agreement, completeness, and consensus.

compute_consensus_batch

Compute deterministic consensus for multiple independent candidate groups.

calculate_population_coverage

Calculate population coverage using a configured authoritative service or exact fixture.

calculate_synthetic_population_coverage

Calculate deterministic demonstration coverage from explicitly synthetic HLA frequencies.

rank_candidates

Calculate deterministic preliminary scores or stable final ranks from completed snapshots.

optimize_shortlist_coverage

Select a stable T-cell shortlist using deterministic construct optimization and set-level coverage.

optimize_construct_genetic

Run a seeded deterministic genetic-style construct optimization with coverage, redundancy, and manufacturability constraints.

calibrate_confidence

Calibrate confidence from score, agreement, completeness, and evidence count without claiming experimental validation.

detect_overlapping_epitopes

Detect positional overlap competitors and connected components without resolving them.

remove_duplicate_candidates

Canonicalize exact duplicate identities while preserving identical peptides at different coordinates.

validate_thresholds

Evaluate documented hard biological thresholds and emit rule outcomes.

categorize_candidates

Assign deterministic decision categories and confidence after scoring and constraints.

apply_constraint_rules

Apply base, duplicate, and overlap rules to one immutable candidate snapshot.

fetch_structure

Fetch or replay a structure record with explicit source provenance.

validate_structure

Validate structure metadata before mapping or docking preparation.

map_epitopes_to_structure

Map epitope candidate coordinates to a validated structure reference.

calculate_surface_accessibility

Calculate fixture-safe surface accessibility summaries for mapped candidates.

calculate_structure_confidence

Calculate structure confidence from provided metrics or fixture-safe defaults.

detect_binding_pockets

Detect binding pockets with fpocket when configured, otherwise fail or fixture-replay.

create_molstar_view

Create a Mol* view-state reference for structure or docking visualization.

fetch_compound

Fetch or replay compound metadata with explicit source provenance.

validate_compound

Validate compound identity and basic molecular string shape before docking.

deduplicate_compounds

Canonicalize compounds by normalized SMILES-like identity.

calculate_molecular_descriptors

Calculate deterministic lightweight descriptor estimates without claiming RDKit execution.

prepare_ligand

Prepare a ligand artifact reference through configured chemistry tooling or fixture fallback.

prepare_receptor

Prepare receptor artifact references for docking through local tools or fixture fallback.

validate_docking_box

Validate docking box dimensions before docking execution.

run_docking

Run configured docking or replay an approved deterministic docking fixture.

cluster_docking_poses

Cluster docking poses from structured docking output.

extract_interactions

Extract interaction summaries from representative docking poses.

generate_report

Generate immutable report artifacts from an approved run.

export_candidates

Export approved candidates with separate raw and normalized score fields.

visualize_results

Build a validated deterministic visualization view model.

explain_candidate

Explain a fixed candidate decision without changing scientific values.

export_workflow_trace

Export a redacted ordered workflow trace without secrets or chain-of-thought.

describe_agentic_workflow

Describe the single NitroStack MCP app internal agent graph, tool permissions, approvals, and final package contract.

run_agentic_workflow

Run the strict PRD v1.1 LangGraph bounded-agent workflow inside the single NitroStack MCP app.

chat_with_research_agent

Answer researcher or judge questions through the bounded agent policy using supplied evidence only.

export_research_package

Return the PRD v1.1 final research package contract and deterministic artifact metadata.