Skip to main content
Glama
125,309 servers. Updated
Browse by product
20 Best Docker MCP Servers: compared and ranked, November 2026Ranked from 1,744 matching servers on stars, growth, downloads and maintenance. Updated .

Matching MCP tools:

Matching MCP Connectors:

"A server that can run Docker Compose commands to manage containers" matching MCP servers:

GET /v1/servers – MCP directory API reference
  • F
    license
    Not graded
    quality
    D
    maintenance
    Audits docker-compose.yml files for security misconfigurations, providing severity ratings, remediation text, and YAML fix snippets for AI agents.
    -
  • F
    license
    Not graded
    quality
    D
    maintenance
    Your AI agent can't touch Stripe, Gmail, Slack or more, without your tap. mild.run intercepts every sensitive action and sends you a notification to approve or block — before anything executes. Agent never holds credentials.
    -
  • A
    license
    A
    quality
    B
    maintenance
    Enables AI coding agents to inspect GitHub repositories and shell commands for download-and-execute payloads, obfuscation, typosquatted dependencies, autorun hooks, and fake-star signals before following or running them.
    3
    MIT
  • A
    license
    Not graded
    quality
    B
    maintenance
    Enables local LLM agents to inspect Docker containers and optionally perform guarded restarts through MCP, with read-only defaults, credential redaction, canonical ID checks, denylists, and bounded daemon timeouts. It provides secure, zero-trust Docker daemon access for MCP clients.
    107
    MIT
  • A
    license
    Not graded
    quality
    B
    maintenance
    Enables AI agents to call tools through a security gateway that intercepts requests, enforces deterministic policy and risk checks, blocks or escalates high-risk actions for human approval, and keeps tool credentials and audit logs protected.
    1
    MIT
  • F
    license
    Not graded
    quality
    D
    maintenance
    A secure MCP server example that demonstrates how to deploy to Google Cloud Run with authentication and identity token protection. Serves as a tutorial template for building production-ready MCP servers in the cloud.
    -
  • A
    license
    Not graded
    quality
    C
    maintenance
    Enables AI agents to request an independent second opinion from a different frontier model, with PII scrubbing before transit, live web search grounding, caching, and multi-provider failover.
    Apache 2.0
  • F
    license
    Not graded
    quality
    D
    maintenance
    This MCP server provides secure access to databases for AI agents, enforcing authentication, authorization, human approval, logging, and notifications to prevent dangerous actions.
    -
  • A
    license
    Not graded
    quality
    B
    maintenance
    Enables AI agents to rehearse risky actions — SQL, shell, git, Terraform, cloud and SaaS operations — against simulations of the real system before executing them, so they can see the consequences first. Returns a consequence report with a safe, confirm or block verdict, blast radius, reversibility and evidence, without ever executing the action itself.
    Apache 2.0
  • A
    license
    Not graded
    quality
    B
    maintenance
    Enables AI agents and MCP clients to call pay-per-use metered MCP endpoints, handle HTTP 402 payment challenges, top up compute packs, and enforce spend authorization with atomic reserve-commit-rollback accounting.
    MIT
  • A
    license
    Not graded
    quality
    C
    maintenance
    Enables LLM clients to query a CRM (local reference CRM or Salesforce) over MCP while enforcing per-user field-level security and record sharing on every query, serving results from an index that stores only ids and hashes rather than text, and re-reading fields live. Retrieved content is sanitized before reaching the model, and the model can only propose CRM writes that a human approves by payload hash.
    Apache 2.0
  • F
    license
    A
    quality
    A
    maintenance
    An MCP server that sends plain-text Gmail messages only to a predefined allowlist, using generated recipient IDs instead of email addresses to enforce security.
    2
    1
    -
  • F
    license
    A
    quality
    C
    maintenance
    Enables local spend caps and Ed25519-signed provenance receipts for AI agent tool calls, allowing any MCP host to gate model usage and independently verify signed decisions without sending prompts or content.
    6
    -
  • A
    license
    Not graded
    quality
    B
    maintenance
    Enterprise MCP gateway that unifies multiple MCP servers behind one governed endpoint, providing federation, authentication, policy enforcement, caching, rate limiting, and audit.
    1
    Apache 2.0
  • A
    license
    Not graded
    quality
    D
    maintenance
    Provides agent certification and trust verification tools for AI agents, enabling certification checks, trust score calculations, audit ticket issuance, and emergency kill switch activation through the A-SOC trust network.
    1 npm
    1
    -
  • A
    license
    Not graded
    quality
    B
    maintenance
    Enables MCP agents to rehearse risky database plans on a no-network clone, measure blast radius and guardrail violations, and apply only approved plans to production when the rehearsal matches.
    MIT
  • A
    license
    Not graded
    quality
    B
    maintenance
    Enables agents to create and unlock KDBX vaults, tune Argon2 and other KDF/cipher settings, manage groups and entries, and retrieve current TOTP codes through a Streamable HTTP MCP endpoint with bearer-token scoping.
    GPL 3.0
  • A
    license
    Not graded
    quality
    F
    maintenance
    Next.js-based MCP server with OAuth 2.1 authentication, deployable on Vercel, supporting SSE and Streamable HTTP transports for various clients.
    88
    MIT
  • F
    license
    Not graded
    quality
    D
    maintenance
    Enables remote execution of 150+ offensive-security tools through a streamable-HTTP MCP server, allowing MCP clients like Claude Code to drive the HexStrike toolset over the network.
    -
  • A
    license
    C
    quality
    Not graded
    maintenance
    Provides access to 20+ Kali Linux penetration testing tools through isolated Docker containers, enabling network scanning, vulnerability assessment, password cracking, web security testing, and forensics through natural language commands.
    26
    1
    MIT
  • A
    license
    Not graded
    quality
    B
    maintenance
    Enables MCP clients to triage SOC alerts while enforcing a trust firewall across retrieval, memory, and privileged actions. It exposes tools for alerts, logs, memory, and alert actions, with defenses that refuse risky operations in the presence of attacker-controllable content.
    MIT
  • A
    license
    Not graded
    quality
    C
    maintenance
    Enables executing arbitrary Joern/CPGQL queries against a loaded Code Property Graph, loading source code in multiple languages (PHP, Java, JavaScript, Python, C/C++) to build new CPGs, and inspecting loaded projects and the active workspace. It communicates with a running Joern server over its synchronous HTTP query endpoint, so no state polling is required.
    GPL 3.0
  • A
    license
    Not graded
    quality
    C
    maintenance
    Enables Claude to list Iceberg tables and run read-only DuckDB SQL queries, including time travel by snapshot, with per-caller token authentication and audit logging.
    MIT
  • A
    license
    Not graded
    quality
    B
    maintenance
    Exposes a fictitious ITSM toolset (ticket search/read, commenting, and closing) behind OAuth bearer-token validation, so clients and users only see and call tools their scope and role allow. It also demonstrates audience binding, so tokens minted for other resources are rejected.
    Apache 2.0
  • F
    license
    Not graded
    quality
    D
    maintenance
    MCP server for IBM QRadar SIEM that consolidates 728 REST API endpoints into 4 intelligent tools, enabling natural language interaction for security tasks like managing offenses, assets, rules, and reference data.
    -
  • A
    license
    A
    quality
    B
    maintenance
    Enables LLM agents to browse and triage vulnerability observations, manage products, branches and rules, import scan reports and SBOMs, run scans and background jobs, and generate VEX documents via SecObserve's REST API.
    18
    78 PyPI
    2
    MIT
  • A
    license
    A
    quality
    B
    maintenance
    An MCP server that checks SPF, DKIM, DMARC, and MX records for a domain, returning a health verdict and specific DNS fixes to improve email deliverability.
    1
    MIT
  • A
    license
    A
    quality
    B
    maintenance
    Lets an agent verify VSL settlement receipts entirely offline and produce signed triggers authorizing a settlement, with the signing key and endpoint fixed at start-up rather than passed in tool calls. When started with an endpoint and token, it can also request a receipt from an issuer, which is the only tool that touches the network.
    1
    Apache 2.0
  • A
    license
    A
    quality
    B
    maintenance
    Enables MCP clients to run read-only passive security audits of public websites, returning a grade, findings, and fixes for each issue. It also checks security headers and security.txt while guarding against SSRF.
    3
    612 npm
    MIT
  • A
    license
    A
    quality
    D
    maintenance
    Enables MCP clients to run Hayabusa detection scans over Windows event log (.evtx) files for forensic analysis and threat hunting.
    2
    MIT
  • A
    license
    A
    quality
    B
    maintenance
    Enables AI agents to read and send email, handle attachments and manage calendar invitations through their own IMAP/SMTP mailboxes, with per-mailbox sender and recipient allow lists and automatic HTML-to-Markdown conversion. It runs as a single self-hosted Docker container, exposing the same tools over MCP and REST.
    15
    15
    MIT
  • A
    license
    A
    quality
    B
    maintenance
    Connect your database to your AI agent, read-only, without sharing your password. Maplith Bridge serves a folder of data files over MCP behind a token you create, and fills it from PostgreSQL under a role that can only read.
    2
    310 npm
    1
    Apache 2.0
  • A
    license
    A
    quality
    B
    maintenance
    Guardrail proxy for AI agents on SQL Server. Each statement runs as the caller's own login, a T-SQL parser blocks dangerous statements, and every statement is audited. Local stdio mode or a central Docker service.
    1
    1
    MIT
  • A
    license
    A
    quality
    C
    maintenance
    Pre-install risk gate for npm packages. Stops AI coding agents from running malicious or lifecycle scripts run.
    1
    2
    MIT
  • A
    license
    A
    quality
    B
    maintenance
    Enables MCP agents to run RouterOS commands on MikroTik routers over SSH, with configurable profiles, secure authentication, and a read-only safety guard.
    3
    16 npm
    MIT
  • A
    license
    A
    quality
    C
    maintenance
    Umbra is the trust layer for AI-generated code. It scores any repo 0-100 with file:line evidence (security, slop, Docker-verified build/boot, and claim receipts that catch agents lying about tests), and guards agent file writes mid-stream blocking leaked keys, alg:none JWTs, and git-hook plants before they land. Tools: scan_repo, guard_content, get_score.
    3
    60 npm
    1
    MIT
  • A
    license
    A
    quality
    B
    maintenance
    Enables MCP hosts such as Claude or Cursor to run multilateral consensus among AI agents of rival owners, enforcing deterministic red lines and max-min decisions over masked verdicts. It also produces tamper-evident SHA-256 receipts that each party can verify and replay against their own private preferences.
    3
    24 PyPI
    1
    Apache 2.0
  • A
    license
    A
    quality
    B
    maintenance
    Guardian is the trust layer for agent commerce. guardian-mcp sits in front of your MCP servers: before a tool call runs, Guardian allows it, asks a person, or denies it, by rules the owner sets, with no AI in the decision. Fails closed. Signed records you can verify offline. Dollar limits on tools that spend money. Free plan: https://odingard.com/guardian
    3
    751 npm
    1
    Apache 2.0
  • A
    license
    A
    quality
    D
    maintenance
    Enforces mandatory human approval before LLM agents can edit files, create files, or execute shell commands, using session tokens and audit logging.
    4
    MIT
  • A
    license
    A
    quality
    C
    maintenance
    Enumerates everything in a code checkout addressed to an AI agent, including instruction files, hook commands, declared MCP servers, and skills/subagents, so you can review what your agent will actually follow.
    5
    55 npm
    1
    MIT
  • A
    license
    A
    quality
    C
    maintenance
    Verum's MCP server turns any codebase into a deterministic, queryable fact layer — an agent can ask who calls a function, what a change impacts, where the dead code and duplicates are, which client calls hit which routes, and run a full security/quality audit. It returns byte-identical answers in a few hundred tokens instead of grepping and reading whole files.
    13
    MIT
  • A
    license
    A
    quality
    D
    maintenance
    A Node.js MCP server that enables Claude Desktop to securely run read-only SQL queries against MariaDB/MySQL and Microsoft SQL Server databases using OAuth 2.0 PKCE authentication. It provides short-lived, per-user credentials that never touch disk, allowing secure database access through natural language interactions.
    5
    MIT
  • A
    license
    A
    quality
    B
    maintenance
    Diagnoses a domain's email authentication — SPF, DMARC, DKIM, MX, blacklists and domain or SSL expiry - and returns copy-paste fix records generated by a validating engine, never a language model. The MCP server is hosted remotely; this repository carries the plugin manifest, connector config and bundled skill.
    27
    3
    Apache 2.0
  • A
    license
    A
    quality
    C
    maintenance
    Lets an LLM explore a cryptic legacy ERP schema in plain language through a semantic layer (table listing, column descriptions, published dictionary) and run single read-only SELECT queries that return capped results. Enforces safety at the database engine level: only reads are authorized, sensitive columns are masked to NULL, queries are aborted after a few seconds, and every call is written to an append-only audit log.
    3
    MIT
  • A
    license
    A
    quality
    B
    maintenance
    qURL is the portal to the invisible internet -- expiring, scope-limited URLs that let AI agents reach services no one else can see.
    17
    1,349 npm
    4
    MIT
  • A
    license
    A
    quality
    B
    maintenance
    Enables AI agents to run private computations on encrypted data using fully homomorphic encryption, supporting operations such as addition, mean, comparison, concatenation, and scientific functions without exposing plaintext inputs.
    6
    18 npm
    18
    MIT
  • A
    license
    A
    quality
    B
    maintenance
    A neutral, public danger grade for MCP servers that AI agents rely on, providing A-F grades and transparency signals to vet servers before connecting.
    3
    MIT
  • A
    license
    A
    quality
    B
    maintenance
    Lets AI agents encrypt a password, API key, or note locally, pay a small USDC fee over x402 on Base, and share a single-use link that can be opened exactly once and is destroyed on read. Reading is free, expiring unread secrets are cleaned up, and the server only ever stores ciphertext.
    10
    MIT
  • A
    license
    A
    quality
    D
    maintenance
    MCP server for connecting to SQL Server in readonly mode. Allows any MCP client to explore the schema and run SELECT queries against a SQL Server database.
    6
    MIT
  • F
    license
    A
    quality
    B
    maintenance
    MCP server for Argo CD and Vault that allows authenticated users to run CLI commands via GitLab SSO, with confirmation for dangerous operations and secret redaction from model context.
    8
    -