Skip to main content
Glama
123,817 servers. Updated

Matching MCP tools:

Matching MCP Connectors:

"Top trending MCP servers currently popular" matching MCP servers:

GET /v1/servers – MCP directory API reference
  • A
    license
    Not graded
    quality
    C
    maintenance
    Enables AI agents and MCP clients to vet on-chain tokens before trading by running a single check_address call that detects honeypots and rug patterns and returns a PASS/WARN/BLOCK verdict with risk score and reasons across Ethereum, BSC, and Solana. Verdicts come from four parallel sources covering honeypot flags, contract audits, liquidity structure, and simulated buy-sell behavior, with graceful degradation flags when a source is unavailable.
    112 npm
    MIT
  • A
    license
    A
    quality
    D
    maintenance
    Exposes PatrowlIntel vulnerability intelligence (CVEs, EPSS, CISA KEV, public exploits, trending attacks) via MCP tools like search_cves, get_cve, and list_trending_attacks.
    3
    2
    MIT
  • A
    license
    A
    quality
    D
    maintenance
    An MCP server for 7-Zip archive operations (list, extract, create) with dual-engine architecture and sandbox security features. Note: currently a learning project and not yet functional.
    3
    2
    MIT
  • A
    license
    A
    quality
    B
    maintenance
    Enables AI agents to query WooCommerce orders through schema-validated MCP tools over stdio or Streamable HTTP, with authentication, host/origin guards, and data minimisation applied before store access. It currently provides read-only order lookup and search, exposing only minimal customer data and safe error responses.
    3
    MIT
  • A
    license
    A
    quality
    C
    maintenance
    Enables guided security evaluation of a virtual lab machine, including network scanning, HTTP/TLS analysis, OWASP Top 10 assessment, and Markdown report generation, without performing exploitation.
    8
    MIT
  • A
    license
    A
    quality
    C
    maintenance
    Human-in-the-loop approval gateway for agent tool calls: agents request, policies decide, humans approve via Slack/Discord/web — with an OWASP-LLM-Top-10-tagged audit trail. Self-hostable.
    10
    18 npm
    33
    MIT
  • F
    license
    A
    quality
    C
    maintenance
    Enterprise-grade zero-dependency security shield and runtime governance engine for MCP servers, providing OWASP MCP Top 10 audits, cryptographic tool call signing, AIBOM generation, and inline parameter firewall protection.
    3
    -
  • A
    license
    B
    quality
    B
    maintenance
    Pre-install gate for AI coding agents. Checks npm, PyPI and crates.io package names before an install runs and blocks names that do not exist, were registered after models invented them, or sit one keystroke from a popular package. CLI, GitHub Action and MCP server. Apache 2.0.
    1
    1
    Apache 2.0
  • A
    license
    B
    quality
    B
    maintenance
    Enables AI agents to use GitHub through MCP while enforcing flow tracking, default-deny policy, human approvals, tamper-evident audit logging, and short-lived scoped tokens to block private-to-public leaks. Currently pre-alpha with only a placeholder tool.
    1
    72 PyPI
    1
    MIT
  • F
    license
    B
    quality
    D
    maintenance
    An MCP server for checking OWASP Top 10 vulnerabilities during API development testing. It analyzes API information and returns security assessment results to help developers identify potential security issues.
    2
    1
    -
  • A
    license
    B
    quality
    D
    maintenance
    A deliberately small MCP server that demonstrates security hardening against the OWASP MCP Top 10 with tools for file search, record queries, and document fetching, each defended against path traversal, SQL injection, and SSRF.
    4
    MIT
  • A
    license
    B
    quality
    C
    maintenance
    A secure MCP server enabling tool calls (kb_search, read_doc, publish_report) through a zero-trust CapabilityBroker with OWASP LLM Top-10 guardrails and human-in-the-loop approval.
    3
    Apache 2.0
  • A
    license
    Not graded
    quality
    B
    maintenance
    Monitor-only proxy for any MCP server: records tool calls with secrets masked, flags instructions hidden in tool definitions, and seals the trace in a tamper-evident hash chain. Also a static scanner for AI agent code, mapped to the OWASP Agentic Top 10. Install: pip install "agentlatch-security[runtime]" Start command: agent-latch-runtime proxy -- python -m agent_latch.runtime.demo_server
    213 PyPI
    11
    MIT
  • A
    license
    Not graded
    quality
    C
    maintenance
    Enables AI agents to build disclosure requests and validate passport, statement, request, and proof-envelope documents, including structural checks of received presentations for audience/nonce binding, expiry, and requirement coverage. It is local and read-only, and currently never accepts presentations because real proof verification and registry support are not yet implemented.
    MIT
  • A
    license
    Not graded
    quality
    C
    maintenance
    Enables remote AI clients to access a private self-hosted server through MCP Streamable HTTP, protected by an embedded OAuth 2.0 + PKCE authorization server and JWT bearer tokens. Currently exposes an authenticated ping tool, with fail-closed security and adversarial-tested authentication flows.
    Apache 2.0
  • A
    license
    Not graded
    quality
    B
    maintenance
    Turns a description of an AI or agentic system's architecture into ranked adversary techniques, coverage-ordered mitigations with assigned owners and components, compounding risks, and real-world incidents of similar shape. Also provides reference lookup and cross-mappings to ATT&CK, STRIDE, OWASP Top 10 for LLM, and NIST AI RMF, entirely offline.
    750 npm
    1
    Apache 2.0
  • A
    license
    Not graded
    quality
    B
    maintenance
    Enables AI agents to run authorized, OWASP Top 10-mapped web-security recon scans against a single target, list available check modules, and inspect optional scanner engine availability, returning severity-ranked findings and explicitly noting checks that found nothing.
    1
    MIT
  • A
    license
    Not graded
    quality
    B
    maintenance
    Cryptographic AI governance and compliance attestation. 75 tools across 80 regulatory frameworks including EU AI Act, NIST AI RMF, NERC CIP, 3GPP R19, OWASP MCP Top 10, CMMC, and SR 11-7. Full OWASP MCP Top 10 coverage. Witness Middleware for zero-code transport-layer compliance. Runtime containment attestation. Distillation provenance. Incident lifecycle chains.
    503 npm
    Apache 2.0
  • A
    license
    Not graded
    quality
    D
    maintenance
    MCP server that audits other MCP servers. Run MCPWatch security scans from inside Claude Code or any MCP-compatible agent with 10 OWASP MCP Top 10 aligned checks and A-F letter grades.
    MIT
  • A
    license
    Not graded
    quality
    C
    maintenance
    Enables voice assistants and other MCP clients to check whether a Polymarket market is safe to cash out, list markets currently in dispute, verify whether paid-for work was actually delivered, and confirm a signed record is genuine using a local ed25519 check. All answers come back as short spoken sentences with full structured details.
    MIT
  • A
    license
    Not graded
    quality
    D
    maintenance
    Passive security scanner that audits a running MCP server against the OWASP MCP Top 10 and grades it A-F. Read-only static analysis of the advertised tools, prompts and resources with console/JSON/SARIF output, and it also runs as an MCP server itself.
    MIT
  • F
    license
    Not graded
    quality
    D
    maintenance
    LLM red-team harness that scans for OWASP LLM Top 10 and MITRE ATLAS vulnerabilities, providing prioritized findings in table, JSON, SARIF, or via an MCP server for AI agents.
    -
  • A
    license
    Not graded
    quality
    B
    maintenance
    Send and verify one-time passcodes over SMS, WhatsApp and Telegram from any MCP client. Ten tools: send, verify, extend, delivery status, account, usage report, and agent account creation with credit top-ups over a 402. Hosted endpoint or run locally.
    1
    MIT
  • A
    license
    Not graded
    quality
    B
    maintenance
    Enables AI agents to investigate email threats by reading the Targeted Attack Protection SIEM feed, searching delivered or blocked threat messages and malicious URL clicks, and drilling into threats, campaigns and sandbox forensics. Also surfaces the most attacked people and top clickers, decodes URL Defense links, and reads Dashboard reports using a separate key.
    Apache 2.0
  • A
    license
    Not graded
    quality
    C
    maintenance
    Enables AI clients to call restricted, group-authorized tools over Streamable HTTP with tamper-evident audit logging; currently provides identity lookup and scratch-note writing.
    Apache 2.0
  • A
    license
    Not graded
    quality
    A
    maintenance
    Enables AI agents to manage API keys and child keys with budgets and spending caps, set plans and model routing, handle wallet payments and top-ups, and verify signed receipts through MCP tools.
    265 npm
    2
    MIT
  • A
    license
    Not graded
    quality
    B
    maintenance
    Enables AI clients (ZCode, Claude Code, Codex, Cursor, Cline) to run shell commands, manage background jobs, and stream files to and from remote Linux servers over SSH through a single authenticated MCP gateway. Target machines' SSH port stays closed to AI and the internet, with token whitelists, command blacklists, confirmations, and audit logging layered on top.
    93 npm
    7
    MIT
  • A
    license
    Not graded
    quality
    C
    maintenance
    A secure-by-default framework for building MCP servers on Azure Entra ID, enforcing OWASP API Security Top 10 controls with authentication, authorization, and rate limiting.
    MIT
  • A
    license
    Not graded
    quality
    C
    maintenance
    Enables querying OWASP security standards, including Top 10 lists for web, API, LLM, and mobile, ASVS 5.0 verification requirements, and defensive cheat sheets via MCP tools or plain-language questions.
    130 npm
    MIT
  • F
    license
    Not graded
    quality
    D
    maintenance
    A deliberately vulnerable MCP server demonstrating API key exposure through hardcoding, plaintext logging, and returning secrets to the model, part of the OWASP MCP Top 10 security lab.
    -
  • F
    license
    Not graded
    quality
    B
    maintenance
    Enables querying Google Analytics 4 properties, metadata, and reports—including realtime, overview, top pages, and traffic sources—through read-only per-user Google OAuth 2.1 authentication. It runs as its own OAuth resource/authorization server, keeping Google tokens encrypted and never exposed to the client.
    -
  • F
    license
    Not graded
    quality
    D
    maintenance
    Enables querying a honeypot threat-intelligence database via natural language to analyze attacker activity, without writing SQL. Provides read-only tools for overview, top attackers, credentials, commands, and more.
    -
  • F
    license
    Not graded
    quality
    D
    maintenance
    An MCP server exposing narrowly scoped storage workflows with Overseer approval integration and redacted execution evidence, currently in fixture-only development for testing via stdio.
    -
  • -
    license
    Not graded
    quality
    Not graded
    maintenance
    Exposes popular OSINT and reconnaissance tools like Sherlock, SpiderFoot, and Holehe through MCP and HTTP APIs for AI assistants. Runs security research tools in sandboxed environments and returns normalized JSON results for investigation and analysis.
    1
    -
  • F
    license
    Not graded
    quality
    B
    maintenance
    Enables users to perform security testing and penetration testing tasks through a Docker-based API that provides access to popular security tools like nmap, nikto, sqlmap, wpscan, dirb, and searchsploit. Designed for educational purposes with input sanitization and non-root execution for safer pentesting workflows.
    -
  • F
    license
    Not graded
    quality
    C
    maintenance
    Institutional MCP server that centralizes access to identity, institutional profiles, and basic person data. Currently a bootstrap with no business logic or tools implemented.
    -
  • A
    license
    A
    quality
    C
    maintenance
    Enables Claude to answer business questions against a company's retail database — sales summaries, top customers, inventory alerts, customer profiles, and plain-English queries — through read-only SQL tools plus a schema resource and reporting prompt. Access is governed by OAuth 2.1 roles and scopes, column-level PII masking, a SQL guard, rate limits, and audit logging.
    5
    MIT
  • A
    license
    A
    quality
    C
    maintenance
    A Model Context Protocol server that gives AI coding agents 16 tools to secure what they build: install the one-line Nemesis Shield SDK, learn/approve/enforce app protection, put a domain behind a Cloudflare-like edge, guard LLMs (OWASP LLM Top 10), and create + score Omniguard business-logic fraud rules. Runs locally over stdio; the discovery tools work with no account.
    16
    90 npm
    MIT
  • A
    license
    A
    quality
    B
    maintenance
    Bawbel MCP Server lets any agent scan MCP servers and skill files for security vulnerabilities mid-conversation. Seven tools covering server-card scanning, conformance scoring, rug pull detection, and AVE threat intelligence queries. Powered by the AVE standard with OWASP MCP Top 10 mapping on every finding. Free, Apache 2.0, no API key required.
    10
    39 PyPI
    2
    Apache 2.0
  • A
    license
    A
    quality
    B
    maintenance
    Enables AI agents to perform read-only forensic triage of Windows disk images over MCP stdio, currently offering MD5/SHA-256 hash calculation and verification confined to an evidence root. Every returned finding carries six-field provenance metadata, while a code-enforced security contract guarantees read-only evidence access, no network or shell use at runtime, structured errors, and an append-only JSONL audit trail.
    1
    MIT