marklogic-mcp
by tternquist
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| ML_SSL | No | Enable HTTPS | false |
| ML_HOST | No | MarkLogic hostname or IP | localhost |
| ML_PORT | No | REST API port | 8000 |
| LOG_LEVEL | No | debug, info, warn, error | info |
| AWS_REGION | No | AWS region for QuickSight integration | (none) |
| LOG_FORMAT | No | json or pretty | json |
| MCP_API_KEY | No | Bearer token for HTTP transport auth | (none) |
| ML_DATABASE | No | Default database | Documents |
| ML_DHF_PORT | No | DHF staging app server port | (ML_PORT) |
| ML_PASSWORD | No | MarkLogic password | admin |
| ML_READONLY | No | Block all write operations | true |
| ML_USERNAME | No | MarkLogic username | admin |
| ML_AUTH_TYPE | No | digest, basic, or oauth | digest |
| FLUX_DATA_DIR | No | Local directory mounted as /data in the Flux Docker container | ./flux-data |
| MCP_HTTP_HOST | No | Bind address for HTTP transport | 0.0.0.0 |
| MCP_HTTP_PORT | No | HTTP transport port | 3000 |
| MCP_TRANSPORT | No | Transport mode: stdio or http | stdio |
| ML_ALLOW_EVAL | No | Enable /v1/eval (XQuery/SJS execution) | false |
| ML_TIMEOUT_MS | No | HTTP request timeout for MarkLogic calls (milliseconds) | 30000 |
| SEMAPHORE_URL | No | Explicit CLS URL override (takes precedence over host:port) | (none) |
| ML_OAUTH_TOKEN | No | Static Bearer token; required in stdio mode when ML_AUTH_TYPE=oauth | (none) |
| SEMAPHORE_HOST | No | Semaphore hostname (enables CLS + KMM connectivity) | (none) |
| FLUX_RUNNER_URL | No | Flux runner HTTP URL (e.g. http://localhost:8082) | (none) |
| MCP_CORS_ORIGIN | No | Restrict CORS to a single origin (default: allow all) | (all) |
| MCP_TRUST_PROXY | No | Express trust proxy setting | (disabled) |
| ML_DHF_JOBS_PORT | No | DHF jobs app server port | (ML_DHF_PORT+2) |
| ML_DHF_CLIENT_JAR | No | Absolute path to marklogic-data-hub-<version>-client.jar | (none) |
| ML_MANAGEMENT_PORT | No | Management API port | 8002 |
| SEMAPHORE_KMM_PORT | No | Studio / KMM port | 5080 |
| SEMAPHORE_PASSWORD | No | KMM password | (none) |
| SEMAPHORE_SCS_PORT | No | Classification Server port | 5058 |
| SEMAPHORE_USERNAME | No | KMM username | (none) |
| FLUX_TIMEOUT_MINUTES | No | Flux operation timeout in minutes | 30 |
| AWS_QUICKSIGHT_ACCOUNT_ID | No | QuickSight account ID | (none) |
| ML_SSL_REJECT_UNAUTHORIZED | No | Reject self-signed SSL certificates (false for dev environments) | true |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
No tools | |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/tternquist/marklogic-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server