Skip to main content
Glama
aiganak-aiops-mcp

aiganak-aiops-mcp

by AiGanak

⚑ AiGanak-AIOps-MCP

Autonomous Infrastructure & Code Health Diagnostic Agent over Model Context Protocol (MCP)
Developed by Akshay Bankar | AiGanak Technologies (aiganak.com) | Released under the Apache 2.0 License.

License: Apache 2.0 Python Version MCP Protocol Orchestrator Observability


🌟 Overview

aiganak-aiops-mcp is a flagship reference architecture and open-source MCP server designed to automate infrastructure diagnostics, log root-cause analysis, and safe code patching.

By combining DuckDB OLAP analytics, Python AST structural inspection, LangGraph cyclic state machines, and Arize Phoenix LLMOps observability, this repository provides a top 1% reference blueprint for production-grade agentic integrations.


Related MCP server: AI Incident Monitoring RCA MCP Server

πŸ“ System Architecture

1. High-Level Protocol & Component Boundaries

    β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”
    β”‚                       Client Layer (IDE / Agent)                            β”‚
    β”‚           (Cursor IDE / Claude Desktop / Custom LangGraph Agent)            β”‚
    β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”¬β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜
                                           β”‚
                                           β”‚ Standard STDIO / JSON-RPC
                                           β–Ό
    β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”
    β”‚                    aiganak-aiops-mcp (FastMCP Server)                       β”‚
    β”‚                                                                             β”‚
    β”‚  β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β” β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β” β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β” β”‚
    β”‚  β”‚    query_log_file      β”‚ β”‚   inspect_code_ast    β”‚ β”‚ apply_code_patch  β”‚ β”‚
    β”‚  β”‚  (DuckDB OLAP Engine)  β”‚ β”‚  (Python AST Parser)  β”‚ β”‚ (Git Safety Gate) β”‚ β”‚
    β”‚  β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”¬β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜ β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”¬β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜ β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”¬β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜ β”‚
    β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”Όβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”Όβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”Όβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜
                   β”‚                          β”‚                       β”‚
                   β–Ό                          β–Ό                       β–Ό
        β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”      β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”    β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”
        β”‚  JSONL/CSV Logs   β”‚      β”‚  Source Code AST  β”‚    β”‚   Host Codebase   β”‚
        β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜      β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜    β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜

2. LangGraph Stateful Self-Healing Orchestrator

                 β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”
                 β”‚       node_log_analyzer        β”‚ <───┐
                 β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”¬β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜     β”‚
                                 β”‚                      β”‚
                                 β–Ό                      β”‚
                 β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”     β”‚
                 β”‚      node_code_inspector       β”‚     β”‚
                 β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”¬β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜     β”‚
                                 β”‚                      β”‚
                                 β–Ό                      β”‚
                 β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”     β”‚
                 β”‚      node_patch_proposer       β”‚     β”‚ (Retry Loop)
                 β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”¬β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜     β”‚
                                 β”‚                      β”‚
                   [ Human Approval Gate Interrupt ]    β”‚
                                 β”‚                      β”‚
                        (Approved / Local)              β”‚
                                 β”‚                      β”‚
                                 β–Ό                      β”‚
                 β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”     β”‚
                 β”‚       node_patch_applier       β”‚     β”‚
                 β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”¬β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜     β”‚
                                 β”‚                      β”‚
                                 β–Ό                      β”‚
                 β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”     β”‚
                 β”‚         node_verifier          β”‚     β”‚
                 β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”¬β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜     β”‚
                                 β”‚                      β”‚
                    [ Verification Passed? ]            β”‚
                     /                    \             β”‚
                  (Yes)                  (No) β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜
                    β”‚
                    β–Ό
                 β”Œβ”€β”€β”€β”€β”€β”
                 β”‚ END β”‚
                 β””β”€β”€β”€β”€β”€β”˜

Available Tools

3 tools
apply_code_patchA

Safely modifies a target Python source file after validating AST syntax and establishing Git safety gates. Automatically rolls back on invalid syntax.

Inputs: file_path (required), new_content (required). Returns: result

inspect_code_astA

Parses a target Python source file into an AST tree to return class, function, and import structures for diagnostic analysis.

Inputs: file_path (required). Returns: result

query_log_fileB

Executes high-speed DuckDB SQL queries directly against log files (JSONL, CSV, Parquet).

Inputs: file_path (required), sql_query (required), max_rows. Returns: result

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    B3.4/5.0

    Scored across 3 tools

    Disambiguation5/5

    Each tool targets a clearly distinct task: log querying, code inspection, and code modification. There is no overlap between querying logs, parsing ASTs, and applying patches, so an agent would not confuse them.

    Naming Consistency2/5

    The naming is inconsistent: query_log_file uses a verb_noun_obj pattern, inspect_code_ast uses verb_noun_obj, but apply_code_patch uses verb_noun. The verbs (query, inspect, apply) are varied and not obviously part of a unified domain vocabulary, and the patterns differ across tools.

    Tool Count3/5

    Three tools is on the borderline of being too thin for an AIOps server, especially given the mixed domain of log analysis and code modification. The count is defensible, but the scope feels narrow for a server with 'aiops' in its name.

    Completeness2/5

    The tools span log querying, code inspection, and code patching, but each area has obvious gaps: there is no tool for writing log query results, no update/get verification for the patch step beyond the patch itself, and the log analysis surface gives no way to define or manage analysis workflows. The domain coverage is fragmented rather than complete.

    Related MCP Connectors

    Related MCP Servers

    • F
      license
      Not graded
      quality
      D
      maintenance
      Provides telemetry tools for retrieving recent logs and system metrics to support root-cause analysis of infrastructure incidents. Enables autonomous incident triage with grounded verification and human-in-the-loop remediation.
      1
      -
    • F
      license
      Not graded
      quality
      D
      maintenance
      Enables autonomous infrastructure health management by exposing tools for retrieving system logs, querying a knowledge base, executing SQL analytics, and simulating system commands, all integrated into an AI-driven incident response workflow.
      -
    • F
      license
      A
      quality
      D
      maintenance
      Enables natural-language diagnosis of Linux system issues by providing sandboxed, typed tools for system, service, filesystem, and git inspection, with human approval for mutating actions.
      18
      -