Skip to main content
Glama
123,820 servers. Updated

Matching MCP tools:

Matching MCP Connectors:

  • A
    license
    A
    quality
    C
    maintenance
    Drop-in stdio interceptor that gates MCP tools/call requests through a YAML policy (block / require_approval / audit / budget cap) before they reach the real server. The same policy file is reused by @jamjet/claude-code-hook and @jamjet/openai-guardrail, so one rule set covers Claude Desktop, Cursor, OpenAI Agents, and custom clients.
    3
    2
    Apache 2.0
  • A
    license
    A
    quality
    B
    maintenance
    Enables deterministic, offline diagnosis of Kubernetes and container failures, generation of exact YAML/Dockerfile fixes, secret and PII redaction, and zero-trust policy checks for agent-proposed commands.
    5
    MIT
  • A
    license
    A
    quality
    D
    maintenance
    Security, cost, and health governance proxy for MCP infrastructure. Enforces YAML-configurable security policies (blocklists, rate limits, token budgets), tracks real token costs via tiktoken, monitors server health with live JSON-RPC probes. Features OAuth 2.1/OIDC with RBAC, web dashboard, payload normalization, semantic shell AST analysis, mTLS, and a formal STRIDE threat model.
    4
    134 npm
    4
    MIT
  • A
    license
    A
    quality
    D
    maintenance
    Converts natural language security requirements into validated Cerbos YAML policies with automated testing and red-team analysis, enabling AI governance with zero-trust guardrails for tool calls, data access, and compliance frameworks.
    5
    3
    Apache 2.0
  • A
    license
    B
    quality
    B
    maintenance
    Enables agents to audit Kubernetes manifests without a cluster: scanning YAML text or whole directories with file:line evidence, browsing the rule catalogue with why/fix rationale, resolving RoleBindings into each subject's effective permissions, and running a self-check that the rules fire.
    5
    MIT
  • A
    license
    Not graded
    quality
    C
    maintenance
    Policy enforcement gateway for MCP tool calls, evaluating every tool invocation against declarative YAML policies (allow/deny/escalate-to-human), generating cryptographic hash-chained audit receipts, and including built-in content safety scanning.
    2
    MIT
  • A
    license
    Not graded
    quality
    B
    maintenance
    Compiles YAML adapters or OpenAPI specs into a minimal MCP tool surface that exposes only declared capabilities to agents, with risk-tiered execution, human approval queues, credential brokering, prompt-injection sanitising and NIST AU-3 audit logging. This lets operators put scoped identity, permissions and kill switches in front of any API so agents can call exactly the tools they need and nothing more.
    3
    MIT
  • A
    license
    Not graded
    quality
    B
    maintenance
    ToolMesh is an Apache-2.0, self-hosted MCP gateway written in Go that sits between AI agents and backend systems. It enforces a fail-closed pipeline on every tool call, including per-tool and per-user authorization, server-side credential injection, structured audit logging, and output policies. APIs are declared in YAML with DADL, turning REST endpoints into MCP tools without writing a custom MCP
    6
    Apache 2.0
  • A
    license
    Not graded
    quality
    B
    maintenance
    72 free, open-source (MIT) developer tools over a stateless, no-key MCP server: JSON/YAML/CSV conversion, PDF and image processing, JWT/hash/UUID utilities, DNS/TLS/HTTP checks, llms.txt and AI SEO checks, and more. Streamable HTTP with JSON responses.
    MIT
  • A
    license
    Not graded
    quality
    C
    maintenance
    Control-plane proxy that sits in front of MCP servers, enforcing per-identity policy (YAML/OPA/Cedar), budget limits, and an audit trail on every call. Includes real-time anomaly detection that auto-blocks a compromised agent without a human in the loop.
    17
    Apache 2.0
  • A
    license
    Not graded
    quality
    C
    maintenance
    mcpwall is a deterministic security proxy for MCP tool calls — iptables for MCP. It sits between the MCP client and server, intercepting every JSON-RPC request and enforcing YAML-defined policies.
    5
    Apache 2.0
  • A
    license
    Not graded
    quality
    C
    maintenance
    Provides AI agents with free, keyless QA and LLM-testing tools over Streamable HTTP, including prompt-injection and PII scans, TLS/header/CORS audits, hallucination and RAG checks, eval contracts, and JSON/YAML/CSV utilities across the full server or three focused packs. Every tool returns an actionable verdict such as a pass/fail, score, or diff.
    MIT
  • A
    license
    Not graded
    quality
    C
    maintenance
    Enables users to define and run MCP tools using declarative YAML configs with built-in trust enforcement, credential brokering, and tamper-evident audit logging.
    14
    MIT
  • A
    license
    Not graded
    quality
    C
    maintenance
    An open-source MCP server that protects AI agents at runtime by evaluating every tool call against YAML policies and generating audit trails.
    1
    Apache 2.0
  • A
    license
    Not graded
    quality
    D
    maintenance
    Acts as an MCP gateway between AI agents and upstream tool servers, evaluating YAML policies on every tool call, injecting real credentials at the last mile, scanning requests and responses for secrets, PII, and prompt injection, and recording each action in a tamper-evident audit log. Also supports HTTP forward-proxy governance with rate limiting, cost tracking, and policy replay against historical audit data.
    4
    Apache 2.0
  • A
    license
    Not graded
    quality
    C
    maintenance
    Enables AML/6AMLD compliance for AI systems, including obliged entity classification, KYC/CDD audits, and sanctions screening.
    MIT
  • A
    license
    Not graded
    quality
    C
    maintenance
    Sits between an agent and an upstream MCP server to enforce per-profile tool grants, deterministic allow/deny/handoff rules, field and PII masking, idempotent writes, and one-line audit logging from a single YAML config. Enables regulated deployments to add guardrails that fail closed without changing the customer's tools or the agent's prompt.
    MIT
  • A
    license
    Not graded
    quality
    B
    maintenance
    Lets AI agents read and propose writes to MariaDB and MySQL databases through MCP without holding database credentials, previewing exactly which rows each write would change, holding risky ones for human approval, and allowing any single change to be undone. Rules in YAML let safe writes through automatically while blocking or escalating the rest.
    1
    AGPL 3.0
  • A
    license
    Not graded
    quality
    B
    maintenance
    A free, local check before your AI agent acts: every tool action is checked against your YAML rules and returns ACT, BLOCK or ESCALATE with an audit record. Optional: send escalations to Flow for a judgment.
    Apache 2.0
  • A
    license
    Not graded
    quality
    C
    maintenance
    A transparent MCP stdio proxy that sits between an agent client and a real MCP server, intercepting tools/call requests to enforce runtime guardrails derived from the same YAML rules used for CI regression testing. It blocks forbidden, out-of-whitelist, looping, or non-idempotent tool invocations with JSON-RPC errors and writes every decision to an audit log.
    1
    MIT
  • A
    license
    Not graded
    quality
    C
    maintenance
    An MCP server that checks Canadian Centre for Cyber Security advisories against the software you actually run, drawn from a YAML stack file, CycloneDX SBOMs, or Docker containers, and reports which advisories affect you, which version fixes them, and when a human needs to verify. It also lets you search, browse, and retrieve individual advisories in English or French, all read-only.
    MIT
  • A
    license
    Not graded
    quality
    C
    maintenance
    Enables an AI to statically audit GitHub Actions workflow files, parsing YAML with accurate line numbers and reporting findings about on: key quirks, expression injection risks, unpinned actions, effective token permissions, and cron scheduling.
    MIT
  • A
    license
    Not graded
    quality
    B
    maintenance
    Enables AI assistants to inspect and safely operate a Linux VPS through typed DevOps tools governed by YAML allowlists, read-only defaults, dry-run plans, secret redaction, and tamper-evident auditing.
    MIT
  • A
    license
    Not graded
    quality
    B
    maintenance
    Guardrail sidecar proxy between AI agents and their MCP/REST/CLI tools. Policy engine, human approval gates, time-limited grants, rate limiting, and OTEL tracing. One Go binary, one YAML config, fail-closed by default.
    1
    Apache 2.0
  • A
    license
    Not graded
    quality
    C
    maintenance
    Enables scanning GitHub Actions workflow YAML for real-world security vulnerabilities such as script injection from attacker-controlled expressions, unpinned third-party actions, missing permissions blocks, and dangerous pull_request_target checkouts. It returns each finding with its exact location, an explanation of the risk, and a concrete remediation.
    MIT
  • A
    license
    Not graded
    quality
    D
    maintenance
    Runtime proxy that intercepts and blocks MCP tool calls based on YAML-defined policies, enforcing security rules for AI agents like Claude Code or Cursor.
    35 npm
    1
    Apache 2.0
  • F
    license
    Not graded
    quality
    D
    maintenance
    AML Watcher MCP Server gives AI agents direct, real-time access to AML Watcher's proprietary sanctions, watchlist, and PEP databases. Connect your agentic workflows to 215+ sanctions regimes, 2.6M+ PEP profiles, and coverage across 235+ countries, no complex integrations required.
    -
  • F
    license
    Not graded
    quality
    D
    maintenance
    A security-focused tool that implements least-privilege credential injection for Claude Code by intercepting Bash and MCP tool calls to swap in minimum-privilege tokens. It enables secure execution of CLI commands and MCP operations by matching tool arguments against declarative YAML policies to prevent unauthorized access.
    -
  • F
    license
    Not graded
    quality
    F
    maintenance
    A secure, declarative MCP runtime that turns YAML configs into MCP servers with trust enforcement, credential brokering, and tamper-evident audit logging.
    -
  • 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
    B
    maintenance
    Enables controlled diagnostics and limited actions on a VPS through safe, auditable tools instead of an unrestricted root terminal, including read-only checks, basic Docker status, allowed-path file reading/searching, and YAML/JSON validation.
    -
  • F
    license
    Not graded
    quality
    C
    maintenance
    Provides internal LLM services with a single MCP endpoint that routes requests to roughly 50 per-app MCP servers (such as ADO and Oracle), applying identity, redaction, authorization, and audit on that hop using a static YAML registry of downstream URLs.
    -
  • A
    license
    A
    quality
    B
    maintenance
    Enables MCP clients to screen blockchain addresses and evaluate payment counterparties before funds move, returning clear/caution/risky verdicts, risk scores, and clickable evidence across EVM chains, Tron, and Solana. It also supports anti-blind-signing checks, x402 payment-requirement verification, identity/control baselines, and signed evidence bundles, with free tools and optional paid compliance tools.
    15
    444 npm
    MIT
  • A
    license
    Not graded
    quality
    B
    maintenance
    Enables AI agents to discover, read and control smart-home devices from multiple vendors through a unified capability model, and to author and trigger YAML scenes that a local deterministic engine executes without the AI in the control loop. High-risk actions such as door locks and garage doors are held in a confirmation queue for a human, and every call is written to a local audit log.
    Apache 2.0
  • 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.
    -