Enrichr MCP Server

1<!--
2 * @Author: tianqitang1 Tianqi.Tang@ucsf.edu
3 * @Date: 2025-06-03 14:18:58
4 * @LastEditors: tianqitang1 Tianqi.Tang@ucsf.edu
5 * @LastEditTime: 2025-06-29 06:46:59
6 * @FilePath: /enrichr-mcp-server/README.md
7-->
8# Enrichr MCP Server
9 
10<div align="center">
11  <img src="icon.svg" alt="Enrichr MCP Server Icon" width="128" height="128">
12</div>
13 
14A Model Context Protocol (MCP) server that provides gene set enrichment analysis using the [Enrichr](https://maayanlab.cloud/Enrichr/) API. This server supports all available gene set libraries from Enrichr and returns only statistically significant results (corrected-$p$ < 0.05) for LLM tools to interpret.
15 
16## Installation
17 
18For Claude Desktop, please download the [Desktop Extension](https://github.com/tianqitang1/enrichr-mcp-server/releases/latest) and install it by clicking `☰ (top left) -> File -> Settings` and drag and drop the downloaded file into the `Settings` window.
19 
20Use the button below to install the MCP server to Cursor, VS Code, or VS Code Insiders with default settings.
21 
22[![Install MCP Server](https://cursor.com/deeplink/mcp-install-dark.svg)](https://cursor.com/install-mcp?name=enrichr-mcp-server&config=eyJjb21tYW5kIjoibnB4IC15IGVucmljaHItbWNwLXNlcnZlciAtLWNvbXBhY3QgLS1tYXgtdGVybXMgMTAwIn0%3D)
23[![Add to VS Code](https://img.shields.io/badge/Add_to_VS_Code-007ACC?style=for-the-badge&logo=visualstudiocode&logoColor=white)](https://vscode.dev/redirect?url=vscode%3Amcp/install%3F%257B%2522name%2522%253A%2522enrichr-mcp-server%2522%252C%2522command%2522%253A%2522npx%2522%252C%2522args%2522%253A%255B%2522-y%2522%252C%2522enrichr-mcp-server%2522%252C%2522--compact%2522%252C%2522--max-terms%2522%252C%2522100%2522%255D%257D)
24[![Add to VS Code Insiders](https://img.shields.io/badge/Add_to_VS_Code_Insiders-24bfa5?style=for-the-badge&logo=visualstudiocode&logoColor=white)](https://vscode.dev/redirect?url=vscode-insiders%3Amcp/install%3F%257B%2522name%2522%253A%2522enrichr-mcp-server%2522%252C%2522command%2522%253A%2522npx%2522%252C%2522args%2522%253A%255B%2522-y%2522%252C%2522enrichr-mcp-server%2522%252C%2522--compact%2522%252C%2522--max-terms%2522%252C%2522100%2522%255D%257D)
25 
26 
27For Claude Code, use the following command:
28```bash
29claude mcp add enrichr-mcp-server -- npx -y enrichr-mcp-server
30```
31 
32## Features
33 
34- **Multi-Library Enrichment Analysis**: Query multiple Enrichr libraries simultaneously (GO, pathways, diseases, tissues, drugs, etc.)
35- **Comprehensive Library Support**: Access to hundreds of gene set libraries from Enrichr including:
36  - Gene Ontology (Biological Process, Molecular Function, Cellular Component)
37  - Pathway databases (KEGG, Reactome, WikiPathways, BioCarta, MSigDB)
38  - Disease/Phenotype databases (Human Phenotype Ontology, GWAS Catalog)
39  - Tissue/Cell type libraries (GTEx, Human Cell Atlas, ARCHS4)
40  - Drug/Chemical libraries (DrugMatrix, L1000, TG-GATEs)
41  - Transcription Factor targets (ChEA, ENCODE)
42  - MicroRNA targets (TargetScan, miRTarBase)
43- **GO Enrichment Analysis**: Specialized tool for GO Biological Process enrichment analysis (I use this a lot, so I made it a tool)
44 
45 
46## Configuration
47 
48### MCP Client Configuration
49 
50Add this server to your MCP client configuration (e.g., `.cursor/mcp.json`):
51 
52#### Basic Configuration (Popular Libraries by Default)
53With the default configuration the server will query a curated list of popular libraries.
54```json
55{
56  "mcpServers": {
57    "enrichr-server": {
58      "command": "npx",
59      "args": ["-y", "enrichr-mcp-server"]
60    }
61  }
62}
63```
64 
65#### Custom Available Libraries Configuration
66 
67You can configure libraries that are available for the LLM to use using CLI arguments in your MCP configuration:
68 
69```json
70{
71  "mcpServers": {
72    "enrichr-popular": {
73      "command": "npx", 
74      "args": ["-y", "enrichr-mcp-server", "--libraries", "pop"]
75    }, // This will make the most popular libraries available to the LLM, namely GO_Biological_Process_2025, KEGG_2021_Human, Reactome_2022, MSigDB_Hallmark_2020, ChEA_2022, GWAS_Catalog_2023, Human_Phenotype_Ontology, STRING_Interactions_2023, DrugBank_2022, CellMarker_2024
76    "enrichr-pathways": {
77      "command": "npx",
78      "args": ["-y", "enrichr-mcp-server", "-l", "GO_Biological_Process_2025,KEGG_2021_Human,Reactome_2022"]
79    },
80    "enrichr-disease": {
81      "command": "npx",
82      "args": ["-y", "enrichr-mcp-server", "--libraries", "Human_Phenotype_Ontology,OMIM_Disease,ClinVar_2019"]
83    }
84  }
85}
86```
87 
88### Command Line Options
89 
90Adjust the CLI options to your needs, unreasonable settings might exceed the context window of the LLM and confuse it, so choose wisely:
91 
92| Option | Short | Description | Default |
93|--------|-------|-------------|---------|
94| `--libraries <libs>` | `-l` | Comma-separated list of Enrichr libraries to query | `pop` |
95| `--max-terms <num>` | `-m` | Maximum terms to show per library | `50` |
96| `--format <format>` | `-f` | Output format: `detailed`, `compact`, `minimal` | `detailed` |
97| `--output <file>` | `-o` | Save complete results to TSV file | _(none)_ |
98| `--compact` | `-c` | Use compact format (same as `--format compact`) | _(flag)_ |
99| `--minimal` | | Use minimal format (same as `--format minimal`) | _(flag)_ |
100| `--help` | `-h` | Show help message | _(flag)_ |
101 
102#### Format Options
103- **`detailed`**: Full details including p-values, odds ratios, and gene lists (default)
104- **`compact`**: Term name + p-value + gene count (saves ~50% tokens)
105- **`minimal`**: Just term name + p-value (saves ~80% tokens)
106 
107#### Examples
108 
109For a full list of commands, options, and usage examples, run the server with the `--help` flag. This is the most up-to-date source of information.
110 
111```bash
112# Show the help message
113npx enrichr-mcp-server --help
114```
115 
116### Environment Variables
117 
118You can also configure the server via environment variables:
119 
120| Variable | Description | Example |
121|----------|-------------|---------|
122| `ENRICHR_LIBRARIES` | Comma-separated list of libraries to query | `GO_Biological_Process_2025,KEGG_2021_Human` |
123| `ENRICHR_MAX_TERMS` | Maximum terms per library | `20` |
124| `ENRICHR_FORMAT` | Output format (`detailed`/`compact`/`minimal`) | `compact` |
125| `ENRICHR_OUTPUT_FILE` | TSV output file path | `/tmp/enrichr_results.tsv` |
126 
127**Note**: CLI arguments take precedence over environment variables when both are specified.
128 
129 
130### Popular Libraries
131 
132This table lists the libraries included when using the `-l pop` flag.
133 
134| Library | Description |
135|---------|-------------|
136| `GO_Biological_Process_2025` | Gene Ontology terms describing biological objectives accomplished by gene products. |
137| `KEGG_2021_Human` | Metabolic and signaling pathways from Kyoto Encyclopedia of Genes and Genomes for human. |
138| `Reactome_2022` | Curated and peer-reviewed pathways from Reactome covering signaling, metabolism, gene expression, and disease. |
139| `MSigDB_Hallmark_2020` | Hallmark gene sets representing well-defined biological states and processes from MSigDB. |
140| `ChEA_2022` | ChIP-seq experiments from GEO, ENCODE, and publications identifying transcription factor-gene interactions from human and mouse. |
141| `GWAS_Catalog_2023` | Genome-wide association study results from NHGRI-EBI GWAS Catalog linking genes to traits. |
142| `Human_Phenotype_Ontology` | Standardized vocabulary of phenotypic abnormalities associated with human diseases. |
143| `STRING_Interactions_2023` | Protein interactions from STRING database including experimental and predicted. |
144| `DrugBank_2022` | Drug targets from DrugBank including approved drugs and experimental compounds. |
145| `CellMarker_2024` | Manually curated cell type markers from CellMarker database for human and mouse. |
146 
147For a complete list of available libraries, visit the [Enrichr Libraries page](https://maayanlab.cloud/Enrichr/#libraries).
148 
149### Benefits of Library Configuration
150 
1511. **Simplified Tool Calls**: When libraries aren't specified in tool calls, your configured libraries are used
1522. **Consistent Results**: Ensures consistent library usage across different queries  
1533. **Multiple Configurations**: Set up different MCP server instances for different research contexts
1544. **Override Capability**: Individual tool calls can still specify different libraries when needed
155 
156## Usage
157 
158The server provides two tools:
159 
160### `enrichr_analysis` (Recommended for multi-library analysis)
161 
162Performs enrichment analysis across multiple specified Enrichr libraries.
163 
164**Parameters:**
165- `genes` (required): Array of gene symbols (e.g., ["TP53", "BRCA1", "EGFR"])
166- `libraries` (optional): Array of Enrichr library names to query (defaults to configured libraries)
167- `description` (optional): Description for the gene list (default: "Gene list for enrichment analysis")
168- `maxTerms` (optional): Maximum number of terms to show per library (default: 50)
169- `format` (optional): Output format: `detailed`, `compact`, `minimal` (default: `detailed`)
170- `outputFile` (optional): Path to save complete results as TSV file
171 
172### `go_bp_enrichment` 
173 
174Performs Gene Ontology (GO) Biological Process enrichment analysis to understand biological functions and processes overrepresented in your gene list. Perfect for interpreting gene expression data, identifying significant biological processes, and uncovering functional implications of genes from RNA-seq, microarray, or other high-throughput experiments.
175 
176**Parameters:**
177- `genes` (required): Array of gene symbols (e.g., ["TP53", "BRCA1", "EGFR"])
178- `description` (optional): Description for the gene list (default: "Gene list for GO BP enrichment")
179- `outputFile` (optional): Path to save complete results as TSV file
180 
181**Returns:**
182All tools return formatted text with significant terms including:
183- Library name and summary statistics
184- Term name and identifier
185- Adjusted P-value and raw P-value (scientific notation)
186- Odds ratio and combined score
187- Overlapping genes with counts
188 
189## Available Library Categories
190 
191Enrichr contains hundreds of gene set libraries organized into categories:
192 
193- **Gene Ontology**: Biological processes, molecular functions, cellular components
194- **Pathways**: KEGG, Reactome, WikiPathways, BioCarta, NCI, HumanCyc, Panther
195- **Disease/Phenotype**: HPO, OMIM, ClinVar, GWAS Catalog, DisGeNET
196- **Tissues/Cell Types**: GTEx, Human Cell Atlas, ARCHS4, Mouse Gene Atlas
197- **Transcription Factors**: ChEA, ENCODE, TRANSFAC, JASPAR
198- **MicroRNA Targets**: TargetScan, miRTarBase, microRNA.org
199- **Drug/Chemical**: DrugMatrix, L1000, TG-GATEs, CTD
200- **Protein Interactions**: BioGRID, STRING, hu.MAP
201- **Literature Mining**: PubMed, Geneshot, Co-expression
202- **Evolutionary**: Cross-species homologs, phylogenetic profiles
203 
204For a complete list of available libraries, visit the [Enrichr Libraries page](https://maayanlab.cloud/Enrichr/#libraries).
205 
206## API Details
207 
208This server uses the Enrichr API:
209- **Add List Endpoint**: `https://maayanlab.cloud/Enrichr/addList`
210- **Enrichment Endpoint**: `https://maayanlab.cloud/Enrichr/enrich`
211- **Supported Libraries**: All libraries available through Enrichr web interface
212 
213## Development
214 
215- **Build**: `npm run build`
216- **Watch**: `npm run watch` (rebuilds on file changes)
217- **Inspector**: `npm run inspector` (debug with MCP inspector)
218 
219## Requirements
220 
221- Node.js 18+
222- TypeScript 5.3+
223- Internet connection for Enrichr API access
224 
225## License
226 
227This project follows the same license as the MCP TypeScript SDK.
228 
229## References
230 
231- Chen EY, Tan CM, Kou Y, Duan Q, Wang Z, Meirelles GV, Clark NR, Ma'ayan A. Enrichr: interactive and collaborative HTML5 gene list enrichment analysis tool. BMC Bioinformatics. 2013; 128(14).
232 
233- Kuleshov MV, Jones MR, Rouillard AD, Fernandez NF, Duan Q, Wang Z, Koplev S, Jenkins SL, Jagodnik KM, Lachmann A, McDermott MG, Monteiro CD, Gundersen GW, Ma'ayan A. Enrichr: a comprehensive gene set enrichment analysis web server 2016 update. Nucleic Acids Research. 2016; gkw377.
234 
235- Xie Z, Bailey A, Kuleshov MV, Clarke DJB., Evangelista JE, Jenkins SL, Lachmann A, Wojciechowicz ML, Kropiwnicki E, Jagodnik KM, Jeon M, & Ma'ayan A. Gene set knowledge discovery with Enrichr. Current Protocols, 1, e90. 2021. doi: 10.1002/cpz1.90
236 
237- [Enrichr](https://maayanlab.cloud/Enrichr/)
238- [Model Context Protocol](https://modelcontextprotocol.io/)
239- [MCP TypeScript SDK](https://github.com/modelcontextprotocol/typescript-sdk)
240