Mukunda Rao Katta
@mukundakatta
AI/ML Engineer | Building agentic workflows & LLM integrations | Anthropic Certified | Open Source |
51
Published Tools
0
Total Stars
10
Weekly Downloads
12
GitHub Followers
683
Public Repos
Published Tools
10 MCP Servers21 Skills20 Agentsacross 6 categoriesllm-trace-sampler-py
Mukunda Katta <[email protected]>
Sample LLM traces by risk, errors, latency, and deterministic ids. Python port of @mukundakatta/llm-trace-sampler.
@mukundakatta/mcpcheck
mukundakatta
Validate MCP (Model Context Protocol) config files for Claude, Cursor, Cline, Windsurf, and Zed. CLI + GitHub Action with SARIF output.
...more@mukundakatta/tool-call-contracts
mukundakatta
Validate LLM tool-call payloads with small JSON-like contracts.
@mukundakatta/codex-skill-kit
mukundakatta
Scaffold and validate Codex skills from the command line.
@mukundakatta/prompt-injection-shield
mukundakatta
Prompt-injection risk scanner for untrusted AI context.
@mukundakatta/model-fallback-planner
mukundakatta
Plan model fallback chains from capability, cost, and health data.
@mukundakatta/tool-permission-gate
mukundakatta
Policy-check agent tool calls before execution.
@mukundakatta/rag-quality-kit
mukundakatta
Heuristic quality metrics for RAG retrieval and grounded answers.
@mukundakatta/rag-staleness-auditor
mukundakatta
Find stale RAG chunks by age, version, and freshness requirements.
@mukundakatta/retrieval-acl-filter
mukundakatta
Enforce document ACLs after retrieval and before prompting.
@mukundakatta/context-window-packer
mukundakatta
Pack context chunks into a budget by relevance and priority.
@mukundakatta/streamparse
mukundakatta
Streaming JSON parser that yields partial valid trees as tokens arrive. Built for LLM tool-call payloads, structured output streams, and any place a regular JSON.parse waits too long.
...more@mukundakatta/agentsnap-mcp
mukundakatta
MCP server: snapshot tests for tool-call traces. Capture, normalize, and diff agent tool-use traces to catch silent regressions. Wraps @mukundakatta/agentsnap for Claude Desktop, Cursor, Cline, Windsurf, and Zed.
...more@mukundakatta/agentfit
mukundakatta
Fit your messages into the LLM context window. Token-aware truncation with multiple strategies (drop-oldest, drop-middle, priority), pluggable tokenizers, zero dependencies.
...more@mukundakatta/system-prompt-leak-scan
mukundakatta
Detect system prompt leakage in model outputs.
io.github.MukundaKatta/agentcast
Structured-output enforcer: extract and validate JSON from messy LLM text.
agentcast-py
Structured output for any LLM call. Validate-and-retry loop for JSON responses; BYO LLM and validator. Python port of @mukundakatta/agentcast.
...moreio.github.MukundaKatta/agentfit
Token-aware message truncation: fit a chat history into your model's context budget.
agentfit-py
Fit your messages into the LLM context window. Token-aware truncation with multiple strategies, pluggable tokenizers. Python port of @mukundakatta/agentfit.
...moreio.github.MukundaKatta/agentguard
Network-egress firewall for agent tools: check URLs against a declarative policy.
io.github.MukundaKatta/agentsnap
Snapshot tests for AI tool-call traces: diff, validate, and catch silent regressions.
io.github.MukundaKatta/agentvet
Validate tool-call args before execution. Returns LLM-friendly retry hints.
agentvet-py
Validate LLM-generated tool args before execution. Wraps tool functions with arg validation, raises ToolArgError with LLM-friendly retry hint. Python port of @mukundakatta/agentvet.
...moreai-eval-forge
Zero-dependency eval harness for LLM and agent regression testing. Scores outputs with exact, contains, regex, JSON, citation, and token-F1 checks.
...moreai-supply-chain-manifest-py
Mukunda Katta <[email protected]>
Build and validate lightweight AI model / data / tool manifests. Python port of @mukundakatta/ai-supply-chain-manifest.
claude-commands-check
Linter for Claude Code slash-command files (.claude/commands/*.md). Validates YAML frontmatter, allowed-tools shape, description quality, and flags hardcoded secrets.
...moreclaude-hooks-check
Linter for Claude Code hooks configuration (the 'hooks' block of settings.json). Validates event names, matcher shape, command entries, and flags dangerous commands or hardcoded secrets.
...moreclaude-skill-check
Linter for Claude Code SKILL.md files. Validates YAML frontmatter, required fields, description length, and common secret patterns.
...morecontext-forge-py
Context engineering toolkit for ranking, packing, and risk-scanning RAG context. Python port of @mukundakatta/context-forge.
...moreeval-flake-detector
Detect flaky LLM eval cases across repeated runs. Pass-rate + standard-deviation per case, with per-case severity. Python port of @mukundakatta/eval-flake-detector.
...morehallucination-risk-meter
Estimate hallucination risk in LLM answers from uncertainty language, unsupported specifics, citations, and context coverage. Python port of @mukundakatta/hallucination-risk-meter.
...morejailbreak-corpus-mini-py
Mukunda Rao Katta <[email protected]>
Small local jailbreak and prompt-injection fixture set for tests. Python port of @mukundakatta/jailbreak-corpus-mini.
llm-cost-guard-py
Estimate LLM request cost and enforce per-request or per-session budgets. Python port of @mukundakatta/llm-cost-guard.
llm-output-sanitizer-py
Sanitize LLM outputs before HTML, SQL, shell, or markdown sinks. Python port of @mukundakatta/llm-output-sanitizer.
llm-response-schema-lite-py
Tiny schema validator for structured LLM responses. Python port of @mukundakatta/llm-response-schema-lite.
llm-usage-report
Parse LLM API response logs (Anthropic, OpenAI, Google) and generate token / cost reports. No framework adoption required.
...moremcp-config-check
Linter for MCP (Model Context Protocol) config files used by Claude Desktop, Cursor, Cline, Windsurf, and Zed. CLI + library API.
...moremcpcheck-py
Lint MCP config files for Claude Desktop, Claude Code, Cursor, Cline, Windsurf, and Zed. Stdlib-only Python port of @mukundakatta/mcpcheck.
...moremodel-fallback-planner-py
Mukunda Katta <[email protected]>
Plan model fallback chains from capability, cost, and health data. Python port of @mukundakatta/model-fallback-planner.
model-router-policy-py
Mukunda Katta <[email protected]>
Policy-based model routing by capability, cost, latency, and privacy. Python port of @mukundakatta/model-router-policy.
partial-json-stream
Streaming JSON parser that yields partial valid trees as tokens arrive. For LLM tool calls, structured outputs, and partial recovery.
...moreprompt-injection-shield-cli
Mukunda Rao Katta
CLI wrapper for prompt-injection-shield-py: scan a file or stdin for prompt-injection patterns.
rag-quality-kit
Heuristic quality metrics for RAG retrieval and grounded answers. Python port of @mukundakatta/rag-quality-kit.
rag-staleness-auditor-py
Find stale RAG chunks by age, version, and freshness requirements. Python port of @mukundakatta/rag-staleness-auditor.
semantic-cache-key
Stable semantic cache keys for LLM requests. Invariant to whitespace, casing, and key ordering; sensitive to model swaps, tool list, and retrieval context. Python port of @mukundakatta/semantic-cache-key.
...moreskillint-py
Lint Claude Code SKILL.md files for frontmatter, required fields, descriptions, and hardcoded secrets. Stdlib-only Python port of @mukundakatta/skillint.
...moreio.github.MukundaKatta/streamparse
Parse partial / truncated / messy JSON for LLM tool calls and structured outputs.
system-prompt-leak-scan
Detect system prompt leakage in LLM model outputs via known patterns, configured-prompt substring matching, and unique fingerprint phrases. Python port of @mukundakatta/system-prompt-leak-scan.
...moretool-call-contracts-py
Validate LLM tool-call payloads with small JSON-like contracts. Python port of @mukundakatta/tool-call-contracts.
tool-result-taint-py
Mukunda Rao Katta <[email protected]>
Track untrusted tool output before it enters prompts or actions. Python port of @mukundakatta/tool-result-taint.
vector-poison-score
Score (query, document) pairs for vector/RAG poisoning signals: vector-text mismatch, instruction-like payloads, NaN, suspiciously round numbers. Python port of @mukundakatta/vector-poison-score.
...more