Sarkari Sahayak
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
Sarkari Sahayak — सरकारी सहायक
Bilingual (Hindi/English) agentic-RAG MCP server over RBI regulations. Every answer cites retrieved passages — or the system refuses.
🚧 Under active development (S4 MCP + REST closed; next: S5 UI / optional MIRACL benches).
Roadmap
S0 Bootstrap (repo skeleton, CI, docs)
S1 Ingestion
S2 Retrieval + benchmarks
S3 Agent (cite-or-refuse)
S4 MCP + REST (
SahayakService, rate limit,/v1/ask,/mcp; Cursor + Claude screenshots indocs/img/)S5 UI + Flight Recorder
S6 Ship v1.0
S7 v1.1 Supersession + Marathi
Related MCP server: RAG Banking Regulatory MCP Server
Quick start
# Day-to-day (lint, unit tests, typecheck without PDF deps)
uv sync --group dev
# S1 ingest / PDF+OCR (CI installs this for pyright)
uv sync --group dev --extra ingest
# S2 harness unit tests (ranx) — also what CI uses with ingest
uv sync --group dev --extra ingest --extra evals
# Local E5 / FlagEmbedding for ingest + bench-quick (not in default CI)
uv sync --group dev --extra ingest --extra evals --extra ml
make check
uv run sahayak versionmake check and GitHub Actions install ingest + evals so pymupdf and ranx resolve. Real embeddings need --extra ml locally. See CONTRIBUTING.md.
Benchmarks (local)
make up
uv sync --group dev --extra ingest --extra evals --extra ml
make bench-quick # IndicQA-hi → docs/results/retrieval.json + .mdOn Apple Silicon, E5 uses MPS when available (PYTORCH_ENABLE_MPS_FALLBACK=1 if needed).
Serve (REST + MCP)
make up
ollama serve # if not already running
uv run sahayak serve # http://127.0.0.1:8000
curl -s http://127.0.0.1:8000/health
# Cursor: .cursor/mcp.json → http://127.0.0.1:8000/mcp
# Claude Desktop: stdio via python -m sahayak.mcp_server (see docs/guide/sahayak/S4-mcp-server.md)Client proof screenshots: docs/img/s4-cursor-mcp-tools.png, s4-cursor-cited-answer.png, s4-claude-desktop-mcp.png.
Agent live smoke (local Ollama)
ollama serve # if not already running
ollama pull qwen3:4b-instruct
uv run pytest -m llm -q # excluded from default CI / make checkSee docs/results/agent-notes.md for measured pass rates.
See docs/guide/ for the full implementation guide and AGENTS.md for contributor rules.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
Certified SEC EDGAR fact memory for AI agents with zero hallucination and filing provenance.
Verified answers for AI agents: only from approved documents, with sources, or a refusal.
India's financial MCP — cards, loans, FDs, insurance, MFs; EMI/SIP/tax calcs; NAV lookup; RAG.
Legal answers from official sources; refuses when no norm is verified.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceEnables natural-language question answering over financial annual reports with source-attributed answers, supporting hybrid retrieval and grounded abstention.-
- AlicenseNot gradedqualityDmaintenanceEnables querying banking regulatory documents via a RAG pipeline with hybrid search and multiple LLM backends.1MIT
- FlicenseNot gradedqualityDmaintenanceEnables document indexing and question answering with Retrieval-Augmented Generation, providing cited answers from user-supplied documents.-
- FlicenseBqualityBmaintenanceEnables natural-language Q&A over multi-source documents (PDF/Markdown/web) with a self-reflective retrieval-augmented agent that cites sources, retries on poor retrieval or grounding, and supports multi-turn memory.2-