elasticsearch-investigation-mcp
by Edrient17
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| ES_URL | Yes | Elasticsearch address (e.g., http://elasticsearch.example.com:9200) | |
| MCP_HOST | No | Bind address for the MCP server process | |
| ES_API_KEY | Yes | Base64-encoded API key (id:secret) with read and view_index_metadata permissions on the log index | |
| ES_HOST_FIELD | No | Field containing the host name, must match Zabbix's host name | host.name |
| ES_MESSAGE_FIELD | No | Field containing the raw log message | message |
| ES_SERVICE_FIELD | No | Field containing the service name | service.name |
| ES_MCP_AUTH_TOKEN | Yes | Bearer token for MCP clients to authenticate | |
| MCP_ALLOWED_HOSTS | No | Comma-separated list of allowed Host headers to defend against DNS rebinding | |
| ES_TIMESTAMP_FIELD | No | Field containing the log timestamp | @timestamp |
| INVESTIGATION_MAX_SHAPES | No | Maximum number of message shapes | 25 |
| ES_ALLOWED_INDEX_PATTERNS | No | Comma-separated list of allowed index patterns. Only '*' is a wildcard, '.' is literal. If empty, all indices allowed by the API key are used. | |
| INVESTIGATION_MAX_FUTURE_HOURS | No | Maximum allowed future time offset (in hours) before treating queries as errors | 2 |
| INVESTIGATION_MAX_WINDOW_HOURS | No | Maximum time span (in hours) a single call can cover | 26 |
| INVESTIGATION_MAX_MESSAGE_CHARS | No | Maximum number of characters for a single message | 600 |
| INVESTIGATION_MAX_RETURNED_LINES | No | Maximum number of log lines returned | 100 |
| INVESTIGATION_MAX_FETCH_DOCUMENTS | No | Maximum number of documents to fetch from Elasticsearch for one answer | 10000 |
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/Edrient17/elasticsearch-investigation-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server