Resume Evidence Mcp

io.github.nimish14Published by GitHub account nimish14v0.1.0Updated Oct 24, 2026

Retrieve grounded resume evidence for a job description using BM25 + evidence reranking

VerifiedSTDIODesktop onlyKnowledge & MemoryAI & ML

Overview

AI-generated overview

Local stdio MCP server that gives coding agents BM25-based retrieval of grounded resume evidence matched to a job description.

What you can do
  • Retrieve resume evidence: BM25 keyword retrieval over resume content for a given job description
  • Rank and ground results: evidence reranking so returned facts are tied to the source resume
  • Support coding agents: packaged as a small, focused tool set for agent workflows
  • No tool list is published, so exact tool names and inputs are not documented here.
When to use it
Useful when you want an assistant to pull relevant, grounded resume facts for a specific job description instead of free-form rewriting, for example when tailoring applications or checking which experience supports a requirement.
Requirements
Runs as a local process over stdio, installed from the npm package resume-evidence-mcp; a Node.js runtime is implied by the npm packaging. No authentication, environment variables or headers are declared. Desktop client only; not executable in a web browser.
Before you install
Resumes contain personal data, so consider what content you load and where it is stored locally. No credentials or network access are declared, but the tool list is unpublished, so verify behavior before use.

Installation

In SourceWeft

  1. Open Resume Evidence Mcp in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

Practical LLM Apps

Clone-and-run AI agents, RAG apps, and MCP servers.

Hand-built examples you can customize and ship — not slide-deck demos.

Works with OpenAI, and several apps run fully local with no API key.

Run one now

Invoice Follow-up Agent

bash
git clone https://github.com/nimish14/practical-llm-apps.gitcd practical-llm-apps/starter_ai_agents/invoice_followup_agentpip install -r requirements.txtcp .env.example .env   # add OPENAI_API_KEYstreamlit run app.py

Chat with PDF

bash
cd practical-llm-apps/starter_ai_agents/chat_with_pdfpip install -r requirements.txtcp .env.example .env   # add OPENAI_API_KEYstreamlit run app.py

Resume Evidence RAG (no API key)

bash
cd practical-llm-apps/rag_apps/resume_evidence_ragpip install -r requirements.txtstreamlit run app.py

Freelance Ops MCP (Cursor / Claude)

bash
cd practical-llm-apps/mcp_servers/freelance-ops-mcpnpm installnpm run buildnpx -y @modelcontextprotocol/inspector node dist/index.js

Add to Cursor MCP settings:

json
{  "mcpServers": {    "freelance-ops": {      "command": "npx",      "args": ["-y", "freelance-ops-mcp"]    }  }}

(After npm publish — until then, point args at node + local dist/index.js.)

Browse templates

Starter AI Agents

AppDescription
Invoice Follow-up AgentDraft polite → firm invoice reminders with tone control and overdue context
Chat with PDFAsk questions about an uploaded PDF with page citations

RAG Apps

AppDescription
Resume Evidence RAGHybrid MiniLM + BM25 retrieval that returns grounded resume facts for a job description

MCP Servers

ServerDescription
freelance-ops-mcpTools for overdue status, tone suggestion, and invoice reminder drafts
resume-evidence-mcpBM25 resume evidence retrieval tools for coding agents

Project goals

  1. Every app: clone → install → run in under 2 minutes
  2. Clear README with problem, pipeline, and limits
  3. MCP servers packaged for npm + MCP Registry
  4. Prefer small, focused tools over mega-frameworks

License

MIT — fork it, ship it, sell it.

Source: README.md at commit 6c2af08

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v0.1.0LatestSep 16, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts