Log Pruner MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| OPENSEARCH_URL | No | URL of OpenSearch cluster (optional, for live API access) | |
| OPENSEARCH_USER | No | Username for OpenSearch authentication | |
| OPENSEARCH_PASSWORD | No | Password for OpenSearch authentication |
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
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| read_logsA | Read an OpenSearch log file (JSON or CSV) and return compact log table. Strips kubernetes metadata, duplicate fields — ~98% token reduction. Supports both HTTP access logs and application logs (auto-detected). Args: path: Path to the OpenSearch JSON or CSV export file. limit: Max entries to return (default 100). status_filter: Only show entries with this HTTP status (e.g. "500", "4xx"). Only applies to HTTP access logs. min_response_time: Only show entries slower than this (ms). Only applies to HTTP access logs. time_from: ISO timestamp lower bound filter (e.g. "2026-06-03T01:05:05Z"). time_to: ISO timestamp upper bound filter. |
| query_logsA | Query OpenSearch directly and return compact log table. Requires OPENSEARCH_URL env var. Args: index: OpenSearch index pattern (e.g. "logs-json-"). query: Lucene query string (e.g. "status:500 AND logs.requestFirstLine:/api/users*"). time_from: ISO timestamp lower bound (e.g. "2026-06-03T01:00:00Z"). time_to: ISO timestamp upper bound. limit: Max entries to fetch (default 50). status_filter: Client-side filter by HTTP status after fetch. min_response_time: Client-side filter by min response time (ms). |
| summarize_logsA | Aggregate log summary: top endpoints, error rates, slowest requests, unique IPs. Provide either path (file) or index (API). Args: path: Path to local OpenSearch JSON file. index: OpenSearch index to query (requires OPENSEARCH_URL env). query: Lucene query string for API mode. time_from: ISO timestamp lower bound for API mode. time_to: ISO timestamp upper bound for API mode. limit: Max entries to analyze (default 200). |
| get_errorsA | Get full detail for non-200 responses (errors). Shows stack traces, log bodies, pod info — everything needed for troubleshooting. Args: path: Path to local OpenSearch JSON file. index: OpenSearch index to query (requires OPENSEARCH_URL env). query: Additional Lucene query for API mode. time_from: ISO timestamp lower bound. time_to: ISO timestamp upper bound. limit: Max error entries to return (default 20). context_before: Number of log entries to show before each error (default 0). Set to 20 to see what happened leading up to the error. |
| get_contextA | Get full log entries around a specific timestamp — like grep -C for logs. Shows what happened before and after an event for troubleshooting. Args: path: Path to local OpenSearch JSON file. index: OpenSearch index to query (requires OPENSEARCH_URL env). timestamp: Center timestamp (ISO format, e.g. "2026-06-03T01:05:05Z"). window_seconds: Seconds before and after timestamp to include (default 5). pod: Optional pod name filter — only show entries from this pod. limit: Max entries to return (default 50). |
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/nrapendra-singh/mcp-log-pruner'
If you have feedback or need assistance with the MCP directory API, please join our Discord server