devops-infra MCP Server
Local cognitive infrastructure for AI coding agents — semantic memory, repository intelligence, and MCP tools to reduce token usage.
Discovered via github-topic:mcp and last synced 3mo ago.
Install instructions not detected yet
Check the source repository for the latest setup steps.
Value
symbol ↔ symbol
Every indexed source file
Semantic concepts extracted from docstrings and identifiers
file → file
Wrong type — validate inputs at function boundary
Quick lookup, factual, single symbol
Description
CogniRepo
Class definitions with base classes
Function call relationships with purpose labels
Object missing attribute — check type, None-guard, or spelling
Score
`.rs`
Files
Recorded query nodes (for retrieval scoring)
class → parent
Description
Function and method definitions with docstrings
1,813
Undefined variable — check imports and scope before use
Timeout — add explicit timeout parameter and retry logic
`.java`
1,122
416
Direction
Cross-agent memory nodes (synced from Claude/Gemini)
query → symbol
Syntax error — run a linter before committing
`.py`
83
Conversation session nodes
file ↔ file
List out of range — guard with `len()` check before access
Cross-file, architectural, ambiguous — full context, best model
Recurring error pattern nodes
concept → symbol
File/IO error — always guard file ops with `try/except OSError`
Extensions
symbol → file
Import failed — verify package is installed and module path is correct
Assertion failed — review invariants; do not use assert in prod
`.go`
Missing dict key — use `.get()` with default or check existence first
Moderate reasoning