MCP servers that ship as code — a repository or a package you install and run locally (usually over stdio). They have no hosted endpoint, so we cannot probe or grade them: instead each one shows its repository, install command, license, stars and when it was last updated.
Collected from GitHub repositories and npm, PyPI, Cargo, Go, Maven, NuGet and RubyGems packages tagged as MCP servers, the official MCP Registry, Docker's MCP catalog, ModelScope, Baidu MCP World, Cline and other public directories; one entry per repository. Each candidate is checked by a language model from its name, description and topics, and only actual MCP servers are listed (not clients, SDKs, lists or skills). Package metadata comes from ecosyste.ms (CC BY-SA 4.0). A server that also offers a hosted endpoint is listed under Remote instead. These entries are not counted in our reachability, verification or readiness statistics.
-
Real-time agentic payment fraud investigation: Kafka + Isolation Forest + LangGraph multi-agent with MCP tools, RAG, human-in-the-loop and eval-gated CI
-
Tigergraph-agentic-fraud-investigationgithub.com/krapanshi/Tigergraph-agentic-fraud-investigationactive
TRACE: graph-backed agentic fraud investigation with TigerGraph, official MCP, Gemini reasoning, local embeddings, policy actions, SARs, and 20 verified cases.
-
The Fraud Investigator Assistant shows how AWS Bedrock, MCP servers, and Strands expert agents can transform fraud investigations. By combining private MCP servers for secure data with open-source MCPs for public intelligence, it speeds up case analysis and ensures compliance, reducing investigation timelines significantly.
MIT-0 ★ 8 -
sample-mcp-fraud-investigation-agentgithub.com/aws-samples/sample-mcp-fraud-investigation-agentactive
Educational AWS sample demonstrating the Model Context Protocol (MCP): a Strands agent on Amazon Bedrock AgentCore investigates synthetic e-commerce fraud over an AgentCore Gateway, with a React dashboard streaming its reasoning. Sandbox only, us-west-2.
MIT-0 ★ 4 -
claimdesk-fraud-mcpupdated this year
MCP server for insurance fraud detection — red flag analysis, fraud risk scoring, pattern detection, SIU referral recommendations, and investigation checklists for all lines of business
npm MIT -
SENGRA is an autonomous fraud investigation agent that uncovers organized fraud rings through multi-hop graph analysis. It leverages WCC, PageRank, Louvain communities, and betweenness centrality, retains entity intelligence across sessions, and visualizes evidence paths behind every decision in a real-time dark ops console.
-
mcp-case-managementgithub.com/zavora-ai/mcp-case-managementupdated this year
Case Management MCP Server — investigations, complaints, fraud disputes, deviations, and incidents across regulated industries: read and gated-write tools for case lifecycle, evidence, tasks, notes, SLA/regulatory clocks, and audit trail
cargo Apache-2.0 -
🛡️ Analyze transactions for fraud using advanced models and tools, providing insights and risk scores to enhance investigation efficiency.
Apache-2.0 ★ 1 -
An MCP server exposing deterministic fraud-investigation tools to AI agents. The rules engine decides what fired; the model only interprets. Includes a controlled study of where agents misused the tools and what fixed it.
-
Agentic fraud investigation for Transakt — Kafka + ML scoring, LangGraph over MCP, human-in-the-loop, A2A, Grafana
-
Read-only Solana MCP server for on-chain financial analysis and fraud investigation, backed by Helius
mcpb MIT -
Real-time fraud detection and case management for Indian payments (UPI, cards), with an AI investigation agent and MCP server.
MIT -
A WebMCP fraud-ring investigation console: your browser agent traces the money on a live map and you freeze the ring with one click.
MIT -
Agentic fraud investigation on TigerGraph: GSQL + MCP + GraphRAG case memory, policy-bound next-best actions, and SARs. HH Goa 2026 · Task 4 · 0neHackers
NOASSERTION -
Double-entry ledger with Kafka fraud detection and a local-LLM investigation agent (LangGraph + MCP), with an eval harness
MIT -
Investigate fraud from Claude, Cursor or any MCP client. Explain any verdict with the evidence behind it, pivot from one signup to every account sharing its device, IP or inbox, check an entity against a cross-operator abuse network, and work the review queue. Read-only by default.
npm MIT -
claimdesk-fraud-detector-mcpupdated this year
MCP server for insurance fraud detection — AI-powered claim fraud scoring, red flag analysis, SIU referral reports, and fraud pattern matching for insurance claims
npm MIT -
Five messy data sources fused into one evidence graph, and an AI agent that investigates it through MCP tools, with every answer backed by evidence ids
MIT -
TrustOra checks who is really getting paid before a PayPal payment is captured. Payee-binding rules, an AI investigator agent and MCP tools for agentic commerce
MIT ★ 10 -
Business data as geometry that AI agents navigate: an MCP server for anomaly, drift, root-cause and chain investigation. Stdio or local HTTP, snapshot sessions, branches, compact JSON for agent context.
Apache-2.0 -
BankShield AI is an agentic decision-support system for banking transaction risk investigation. Engineered with a LangGraph state machine and Model Context Protocol (MCP 2.0), it coordinates 4 specialized agents to automate evidence research, evaluate deterministic risk rules (0–100), audit math integrity, and generate 16-field regulatory dossiers.
MIT