Koskamo

Find your next MCP server

Find remote and local MCP servers by task, transport, capability, access, and publisher, with clear verification labels.

26,581 MCP servers

Vendor-operated and community listings, with live-check and source-verification states shown independently.

Showing 9,529–9,540 of 26,581 servers

Sorted by name, A–Z

ServerTypeCategoryAccessSetup
@guardbee/mcp-server-auditor MCP logo, by GuardBee

@guardbee/mcp-server-auditor MCP

By GuardBee · 0 tools

Scans other MCP servers' tool definitions for insecure patterns including excessive agency, shell/eval/SQL/SSRF sinks, loose schemas, hardcoded secrets, and wildcard CORS.

CommunityPackage
Developer toolsSource reviewed
@guardbee/mcp-tool-poisoning-scanner logo, by GuardBee

@guardbee/mcp-tool-poisoning-scanner

By GuardBee · 0 tools

A security scanner for Model Context Protocol (MCP) servers that detects tool poisoning attacks and confused-deputy vulnerabilities.

CommunityPackage
Developer toolsSource reviewed
GuardBee Memory Poisoning Scanner MCP logo, by GuardBee

GuardBee Memory Poisoning Scanner MCP

By GuardBee · 0 tools

Scans agent code for memory poisoning, detecting untrusted input written into persistent, cross-session memory such as MemGPT-style archival or long-term vector stores that is…

CommunityPackage
AI and machine learningSource reviewed
GuardBee Model Scanner MCP logo, by GuardBee

GuardBee Model Scanner MCP

By GuardBee · 0 tools

Scans ML model files including PyTorch, pickle, safetensors, Keras/H5, and ONNX formats for supply-chain risks such as dangerous pickle deserialization globals, disguised or…

CommunityPackage
AI and machine learningSource reviewed
GuardBee Prompt Injection Scanner MCP logo, by GuardBee

GuardBee Prompt Injection Scanner MCP

By GuardBee · 0 tools

A community MCP server that scans RAG content and scraped pages for indirect prompt injection attacks.

CommunityPackage
AI and machine learningSource reviewed
GuardBee Prompt Leak Scanner MCP logo, by GuardBee

GuardBee Prompt Leak Scanner MCP

By GuardBee · 0 tools

A security-focused MCP server component that detects leaked credentials and personally identifiable information (PII) such as API keys, credit cards, and national IDs within…

CommunityPackage
AI and machine learningSource reviewed
GuardBee Reverse Shield MCP logo, by GuardBee

GuardBee Reverse Shield MCP

By GuardBee · 0 tools

Audits shipped web builds, Electron apps, Android APKs, iOS IPAs, and native binaries for reverse engineering risks.

CommunityPackage
Developer toolsSource reviewed
GuardBee Secret Scanner MCP logo, by GuardBee

GuardBee Secret Scanner MCP

By GuardBee · 0 tools

An MCP server that scans files, git history, or agent transcripts for leaked secrets and API keys.

CommunityPackage
Developer toolsSource reviewed
GuardBee Security Suite MCP logo, by GuardBee

GuardBee Security Suite MCP

By GuardBee · 0 tools

A bundle of security tools including secret-scanner, dependency-auditor, ssl-inspector, and dns-intelligence.

CommunityPackage
Developer toolsSource reviewed
GuardBee Slopsquat Scanner MCP logo, by GuardBee

GuardBee Slopsquat Scanner MCP

By GuardBee · 0 tools

A community MCP server that audits project dependency manifests against real npm and PyPI registries to detect slopsquatting attacks.

CommunityPackage
Developer toolsSource reviewed
GuardBee SSL Inspector MCP logo, by GuardBee

GuardBee SSL Inspector MCP

By GuardBee · 0 tools

An MCP server that performs TLS certificate, cipher, and protocol inspection.

CommunityPackage
Developer toolsSource reviewed
GuardBee Unbounded Consumption Auditor MCP logo, by GuardBee

GuardBee Unbounded Consumption Auditor MCP

By GuardBee · 0 tools

This MCP server scans LLM and agent application code to identify Unbounded Consumption risks, also known as denial-of-wallet attacks.

CommunityPackage
Developer toolsSource reviewed

Browse by category

Let your agent find its tools

Add Koskamo to your agent to find official MCP servers for a task, inspect access requirements, and get setup links. Public discovery needs no key.

How listings and verification work

Remote listings are live-checked and re-checked weekly. Local packages are validated from their attributed registry or catalog source and are never executed by Koskamo. Community and vendor evidence are labelled separately.

Access labels describe remote connection and discovery. Individual tools may require accounts, credentials, permissions, or payment. Registry membership and endpoint checks are not security audits.

Operators can list their own server through the public API or the koskamo_register_mcp_server MCP tool: prove control of the endpoint's domain with a well-known file or a DNS TXT record, pass the live check, and it is published at once. Proofs are re-checked weekly. Admins can still hide or remove any listing.

List your own server