MCP-Gateway

MCP Gateway, a new tool and capability gateway, allows AI clients to access unlimited backend tools without loading every tool definition into the context window, reducing token overhead by up to 89%. The system replaces hundreds of tool definitions with a compact 14-17 tool Meta-MCP surface, discovering the correct backend tool on demand, and supports REST APIs via YAML files or OpenAPI specs instead of requiring dedicated MCP servers. The gateway eliminates the tradeoff between tool quantity and context limits, with benchmarks showing a cost reduction from $0.22 to $0.024 per request at scale.

Give your AI access to every tool it needs -- without burning your context window or building MCP servers. Five MCP hot-reload tools compared https://ruachtov.ai/blog/five-tools-mcp-restart.html -- Ruach Tov Collective's BPD-based comparison of mcp-gateway against four restart-focused alternatives. Includes a feature matrix and architectural analysis. mcp-gateway deep dive https://ruachtov.ai/blog/mcp-gateway-deep-dive.html -- Detailed walkthrough of the capability system, SHA-256 integrity pinning, and the v2.5-to-v2.9 development arc. MCP Gateway sits between your AI client and your tools. Instead of loading hundreds of tool definitions into every request, the AI gets a compact Meta-MCP surface -- 14 tools minimum, 16 in the README benchmark scenario, 17 when webhook status is surfaced -- and discovers the right backend tool on demand. Public quantitative claims in this README are sourced from docs/BENCHMARKS.md /MikkoParkkola/mcp-gateway/blob/main/docs/BENCHMARKS.md and the machine-readable benchmarks/public claims.json /MikkoParkkola/mcp-gateway/blob/main/benchmarks/public claims.json , with CI checks to catch drift. MCP Gateway is a tool and capability gateway . It routes MCP tool/resource/prompt traffic to backend MCP servers and capability-backed REST APIs, and it can proxy MCP server-to-client requests like sampling/createMessage , elicitation/create , and roots/list back to the connected client over the existing gateway session. MCP Gateway is not a general OpenAI/Anthropic chat completions or embeddings gateway. When a backend asks for sampling/createMessage , the connected client still performs the model call. The OpenAI-compatible prompt-cache helpers in the gateway exist only so gateway invoke can preserve prompt cache key behavior for backends or capabilities that happen to call LLM APIs internally. The context window is the bottleneck. Every MCP tool you connect costs ~150 tokens of context overhead. Connect 20 servers with 100+ tools and you've burned 15,000 tokens before the conversation starts -- on tool definitions the AI probably won't use this turn. Worse: context limits force you to choose which tools to connect. You leave tools out because they don't fit -- and your AI makes worse decisions because it can't reach the right data. MCP Gateway removes that tradeoff entirely. | Without Gateway | With Gateway | | |---|---|---| Tools in context | Every definition, every request | 16 Meta-MCP tools in the README benchmark ~1600 tokens | Token overhead | ~15,000 tokens 100 tools | ~1600 tokens -- 89% savings | Cost at scale | ~$0.22/request Opus input | ~$0.024/request -- $201 saved per 1K | Practical tool limit | 20-50 tools context pressure | Unlimited -- discovered on demand | Connect a new REST API | Build an MCP server days | Drop a YAML file or import an OpenAPI spec minutes | Changing MCP config | Restart AI session, lose context | Restart gateway ~8ms , session stays alive | When one tool breaks | Cascading failures | Circuit breakers isolate it | The base discovery quartet gateway list servers , gateway list tools , gateway search tools , gateway invoke stays constant. The README benchmark scenario also surfaces stats, cost report, playbooks, profile controls, disabled-capability visibility, and reload for a 15-tool surface. Surfacing webhook status adds the 16th tool. | Alternative | What it does | Why MCP Gateway is different | |---|---|---| Direct MCP connections | Each server connected individually | Every tool definition loaded every request. 100 tools = 15K tokens burned. Gateway: a small fixed 13-16 tool surface instead of every backend tool. | Claude's ToolSearch | Built-in deferred tool loading | Only works with tools already configured. Gateway adds unlimited backends + REST APIs without MCP servers. | Archestra | Cloud-hosted MCP registry | Requires cloud account, sends data to third party. Gateway is local-only, zero external dependencies. | Kong / Portkey | General API gateways | Not MCP-aware. No meta-tool discovery, no tool search, no capability YAML system. | Building fewer MCP servers | Reduce tool count manually | You lose capabilities. Gateway lets you keep everything and pay the token cost of the compact Meta-MCP surface. | On 2026-05-19 Anthropic shipped Claude Managed Agents https://claude.com/blog/claude-managed-agents-updates with self-hosted sandboxes public beta and MCP tunnels https://platform.claude.com/docs/en/agents-and-tools/mcp-tunnels/overview research preview . MCP tunnels let a Claude agent reach a single MCP server inside a private network through one outbound connection from a lightweight gateway -- no inbound firewall rules, no public endpoint, encrypted end-to-end. mcp-gateway and Anthropic's MCP tunnel sit at different layers and compose . The tunnel is reachability plumbing for one private MCP server. mcp-gateway is the aggregation, routing, capability-namespacing and observability layer across many MCP and REST backends. When both are deployed, mcp-gateway becomes the private MCP server that Anthropic's tunnel exposes -- one tunnel, one outbound connection, every backend behind it. | Concern | Anthropic MCP tunnel | mcp-gateway | Boundary | |---|---|---|---| Backend topology | Single MCP server per tunnel, exposed through one outbound connection | src/gateway/ , capabilities/ .yaml Tool routing gateway search tools / gateway invoke discovery src/gateway/ ; SHA-256 pinning per capability src/capability/hash.rs Observability trace id and cost-accounting across every backend invocation src/cost accounting/ , src/gateway/ Complementary, not a replacement. A team that wants Claude Managed Agents to reach a private-network deployment of mcp-gateway uses the tunnel for reachability and mcp-gateway for fan-out, capability hygiene, OWASP Agentic AI controls docs/OWASP AGENTIC AI COMPLIANCE.md /MikkoParkkola/mcp-gateway/blob/main/docs/OWASP AGENTIC AI COMPLIANCE.md , and unified cost / trace telemetry. The two solve adjacent problems. Connecting N MCP servers to an agent means accepting N attack surfaces. Tool poisoning, rug pulls, and exfiltration via hidden instructions in tool descriptions are demonstrated attacks, not hypotheticals. Invariant Labs' writeup MCP Security Notification: Tool Poisoning Attacks https://invariantlabs.ai/blog/mcp-security-notification-tool-poisoning-attacks and Simon Willison's summary MCP has prompt injection security problems https://simonwillison.net/2025/Apr/9/mcp-prompt-injection/ lay out the threat model. mcp-gateway puts every backend tool description behind one audit surface and defends it structurally: Tool-poisoning validator AX-010 . Every backend tool description is scanned before it reaches the agent's context window. HIGH patterns fail-closed: <IMPORTANT blocks, ~/.ssh / ~/.aws / id rsa / .env / /etc/passwd , sidenote exfiltration language, curl . https?:// , base64 in exfil context. MEDIUM patterns warn: 40+ consecutive spaces, zero-width / bidi-override Unicode, oversized descriptions. Implementation: 19 tests . src/validator/rules/tool poisoning.rs SHA-256 capability hash-pinning. mcp-gateway cap pin <file writes a sha256: line over the file's canonical hash grep -v '^sha256:' capability.yaml | sha256sum is reproducible from any shell . The loader refuses any mismatched file on load and on every watcher event. Rug-pull detection. When a pinned capability's on-disk content changes after approval, the watcher unloads it and logs RUG-PULL DETECTED . The capability stays quarantined until an operator re-pins. Implementation:and src/capability/hash.rs detect rug pulls in. src/capability/backend.rs Centralized audit surface. Capability YAMLs are plain text, diffable, grep-able, PR-reviewable. The agent only ever sees the compact Meta-MCP surface 13-16 tools . No N-server tool-list pollution means no N-server attack surface. Full walkthrough, PoC snippets, and roadmap: docs/blog/security-aware-mcp-gateway.md /MikkoParkkola/mcp-gateway/blob/main/docs/blog/security-aware-mcp-gateway.md . OWASP Agentic AI Top 10. Controls are mapped across all 10 risks, with explicitly tracked partial/out-of-scope gaps for multi-gateway signing, tool-result sandboxing, collusion detection, and remote-server provenance. See docs/OWASP AGENTIC AI COMPLIANCE.md /MikkoParkkola/mcp-gateway/blob/main/docs/OWASP AGENTIC AI COMPLIANCE.md . OpenAPI importer. mcp-gateway cap import <spec-url-or-file turns an OpenAPI 3 spec into one validated capability YAML per operation. The full Swagger Petstore spec becomes 19 validated capability YAMLs end-to-end:22 tests across python mcp-gateway cap import https://petstore3.swagger.io/api/v3/openapi.json --output capabilities/ --prefix petstore and src/capability/openapi.rs . tests/openapi import tests.rs Tell your AI assistant recommended : Read https://github.com/MikkoParkkola/mcp-gateway and install mcp-gateway to consolidate all my MCP servers behind one gateway Your agent will install the binary, run the setup wizard, import your existing MCP servers, and wire itself up. Works in Claude Code, Cursor, Windsurf, Codex, and any AI with terminal access. Or four commands: brew install MikkoParkkola/tap/mcp-gateway 1. install mcp-gateway setup wizard --configure-client 2. import existing servers + wire up clients mcp-gateway serve 3. run mcp-gateway doctor 4. verify everything is healthy That's it. Your AI clients now talk to the gateway and the gateway routes to every backend you already had configured — at a flat ~15 tools instead of ~150 . Start with gateway search tools from your AI client to find any backend tool, then invoke it with gateway invoke . Nothing to import yet? mcp-gateway init --with-examples writes a working gateway.yaml with public capabilities so you can confirm the gateway is alive before adding your own servers. | Method | Command | |---|---| Homebrew macOS/Linux, recommended | brew install MikkoParkkola/tap/mcp-gateway | Cargo | cargo install mcp-gateway | cargo-binstall | cargo binstall mcp-gateway | Direct binary download Windows x64 | Download mcp-gateway-windows-x86 64.exe from the | Docker | docker run -v $ pwd /gateway.yaml:/config.yaml ghcr.io/mikkoparkkola/mcp-gateway:latest --config /config.yaml | Direct binary download macOS Apple Silicon curl -L https://github.com/MikkoParkkola/mcp-gateway/releases/latest/download/mcp-gateway-darwin-arm64 -o mcp-gateway && chmod +x mcp-gateway macOS Intel curl -L https://github.com/MikkoParkkola/mcp-gateway/releases/latest/download/mcp-gateway-darwin-x86 64 -o mcp-gateway && chmod +x mcp-gateway Linux x86 64 curl -L https://github.com/MikkoParkkola/mcp-gateway/releases/latest/download/mcp-gateway-linux-x86 64 -o mcp-gateway && chmod +x mcp-gateway Windows x64 PowerShell Invoke-WebRequest -Uri https://github.com/MikkoParkkola/mcp-gateway/releases/latest/download/mcp-gateway-windows-x86 64.exe -OutFile mcp-gateway.exe mcp-gateway setup wizard --configure-client Scans Claude Desktop, Claude Code, Cursor, Zed, Continue.dev, Codex, and running MCP processes; lets you pick which servers to import into gateway.yaml ; and writes the gateway entry back into each detected client config so they route through the gateway instead. Add --yes to skip the prompts and import everything. 48 popular MCP servers are pre-registered with the right command, args, and env-var template. mcp-gateway add is claude mcp add / codex mcp add compatible: mcp-gateway add tavily known server, fills env vars mcp-gateway add my-server -- npx -y @some/mcp-server --flag arbitrary stdio command mcp-gateway add --url https://mcp.sentry.dev/mcp sentry HTTP server mcp-gateway add -e API KEY=xxx my-server -- npx my-mcp-server mcp-gateway list shows what's configured. mcp-gateway remove <name removes one. For the full schema reference, see docs/QUICKSTART.md configuration /MikkoParkkola/mcp-gateway/blob/main/docs/QUICKSTART.md configuration . Minimal example: server: port: 39400 meta mcp: enabled: true backends: tavily: command: "npx -y @anthropic/mcp-server-tavily" description: "Web search" env: TAVILY API KEY: "${TAVILY API KEY}" sentry: http url: "https://mcp.sentry.dev/mcp" description: "Sentry issues" mcp-gateway serve start the gateway mcp-gateway doctor diagnose config, port, env vars, backend health mcp-gateway doctor --fix auto-fix issues where possible The web dashboard is at http://localhost:39400/ui http://localhost:39400/ui once serve is running. setup export writes the gateway entry into client config files for you. It auto-detects the right path per client: mcp-gateway setup export --target all all detected clients mcp-gateway setup export --target claude-code one client mcp-gateway setup export --target all --dry-run preview without writing mcp-gateway setup export --target all --watch regenerate on gateway.yaml changes | Client | Config path | |---|---| claude-code | ~/.claude.json | claude-desktop | platform-specific | cursor | .cursor/mcp.json workspace | vs-code-copilot | .vscode/mcp.json workspace | windsurf | ~/.codeium/windsurf/mcp config.json | cline | .cline/mcp servers.json workspace | zed | ~/.config/zed/settings.json | Modes: --mode proxy HTTP , --mode stdio subprocess , --mode auto probe health endpoint, fall back . Manual JSON snippet if you prefer to edit by hand { "mcpServers": { "gateway": { "type": "http", "url": "http://localhost:39400/mcp" } } } The gateway exposes 14 Meta-MCP tools minimum, 16 in the README benchmark scenario, and 17 when webhook status is surfaced. The base discovery quartet stays fixed; the rest are operator helpers for stats, cost, playbooks, profile control, disabled-capability visibility, reload, and webhook status. Token math Claude Opus @ $15/M input tokens, reproducible via python benchmarks/token savings.py --scenario readme : Without : 100 tools x 150 tokens x 1,000 requests = 15M tokens = $225 With README benchmark : 16 Meta-MCP tools x 100 tokens x 1,000 requests = 1.6M tokens = $24.00 Turn any REST API into a tool by dropping a YAML file ~30 seconds or importing an OpenAPI spec: python mcp-gateway cap import stripe-openapi.yaml --output capabilities/ --prefix stripe The gateway ships with 110+ built-in capabilities -- weather, Wikipedia, GitHub, stock quotes, package tracking, and more. Capability YAMLs hot-reload automatically after file changes, no restart needed. mcp-gateway now ships HeyGen video-generation capabilities in capabilities/media/ : video agent create video create video get video download voice list avatar list Setup: export HEYGEN API KEY=your-api-key Make sure your config loads the built-in capability directory: capabilities: enabled: true directories: - ./capabilities The request schemas ship hand-written for the initial connector, but HeyGen's CLI can act as the schema source of truth for future regeneration: heygen video-agent create --request-schema heygen video create --request-schema Map that JSON into each capability's schema.input block when refreshing the connector. Example end-to-end workflow: 1. Create the video with the Video Agent CREATE=$ curl -s http://127.0.0.1:39401/mcp \ -H 'Content-Type: application/json' \ -d '{ "jsonrpc":"2.0", "id":1, "method":"tools/call", "params":{ "name":"gateway invoke", "arguments":{ "backend":"capabilities", "tool":"video agent create", "args":{"prompt":"A presenter explaining our product launch in 30 seconds"} } } }' VIDEO ID=$ printf '%s' "$CREATE" | jq -r '.result.content 0 .text | fromjson | .data.video id // .video id ' 2. Poll until completed and fetch the downloadable URL VIDEO URL=$ while true; do BODY=$ curl -s http://127.0.0.1:39401/mcp \ -H 'Content-Type: application/json' \ -d "{ \"jsonrpc\":\"2.0\", \"id\":1, \"method\":\"tools/call\", \"params\":{ \"name\":\"gateway invoke\", \"arguments\":{ \"backend\":\"capabilities\", \"tool\":\"video get\", \"args\":{\"video id\":\"$VIDEO ID\"} } } }" STATUS=$ printf '%s' "$BODY" | jq -r '.result.content 0 .text | fromjson | .data.status // .status ' if "$STATUS" = "completed" ; then printf '%s' "$BODY" | jq -r '.result.content 0 .text | fromjson | .data.video url // .video url ' break fi sleep 5 done 3. Download and save a local MP4 curl -s http://127.0.0.1:39401/mcp \ -H 'Content-Type: application/json' \ -d "{ \"jsonrpc\":\"2.0\", \"id\":1, \"method\":\"tools/call\", \"params\":{ \"name\":\"gateway invoke\", \"arguments\":{ \"backend\":\"capabilities\", \"tool\":\"video download\", \"args\":{\"video url\":\"$VIDEO URL\"} } } }" \ | jq -r '.result.content 0 .text | fromjson | .data' \ | base64 --decode heygen-explainer.mp4 Your AI connects once to localhost:39400 . Behind it, capability YAMLs plus reloadable gateway config sections including backend add/remove/update and routing/profile changes can reload live via file watching, gateway reload config , or POST /ui/api/reload . Listener address changes report restart required ; env files list changes stay startup-only and take effect after restart. Your AI session stays connected. Circuit breakers, retry with backoff, rate limiting, health checks, graceful shutdown, and concurrency limits. One flaky server won't take down your toolchain. ┌───────────────────────────────────────────────────────────────┐ │ MCP Gateway :39400 │ │ ┌─────────────────────────────────────────────────────────┐ │ │ │ Meta-MCP: 13-16 Tools + Surfaced Tools │ │ │ │ • gateway list servers • gateway search tools │ │ │ │ • gateway list tools • gateway invoke │ │ │ └─────────────────────────────────────────────────────────┘ │ │ │ │ ┌─────────────────────────────────────────────────────────┐ │ │ │ Failsafes: Circuit Breaker │ Retry │ Rate Limit │ │ │ └─────────────────────────────────────────────────────────┘ │ │ │ │ │ ┌──────────────────┼──────────────────┐ │ │ ▼ ▼ ▼ │ │ ┌─────────────┐ ┌─────────────┐ ┌─────────────┐ │ │ │ Tavily │ │ Context7 │ │ Pieces │ │ │ │ stdio │ │ http │ │ sse │ │ │ └─────────────┘ └─────────────┘ └─────────────┘ │ └───────────────────────────────────────────────────────────────┘ Embedded web UI at /ui -- live status, searchable tools, server health, config viewer. Operator dashboard at /dashboard . Cost tracking at /ui costs . All served from the same binary and port, no frontend build step. | Feature | Description | Docs | |---|---|---| Authentication | Bearer tokens, API keys, explicit admin keys, per-client rate limits and opt-in per-client circuit breakers | | Per-Client Tool Scopes examples/per-client-tool-scopes.yaml /MikkoParkkola/mcp-gateway/blob/main/examples/per-client-tool-scopes.yaml Security Firewall CHANGELOG /MikkoParkkola/mcp-gateway/blob/main/CHANGELOG.md 260---2026-03-13 Cost Governance CHANGELOG /MikkoParkkola/mcp-gateway/blob/main/CHANGELOG.md 260---2026-03-13 Session Sandboxing CHANGELOG /MikkoParkkola/mcp-gateway/blob/main/CHANGELOG.md 250---2026-03-12 mTLS CHANGELOG /MikkoParkkola/mcp-gateway/blob/main/CHANGELOG.md 240---2026-02-25 | Feature | Description | |---|---| Capability System | REST API to MCP tool via YAML. Hot-reloaded. | Transform Chains Example /MikkoParkkola/mcp-gateway/blob/main/examples/transform-example.yaml . Webhooks Docs /MikkoParkkola/mcp-gateway/blob/main/docs/WEBHOOKS.md . Auto-Discovery Surfaced Tools tools/list for one-hop invocation. Semantic Search Tool Profiles Config Export mcp-gateway config export MCP Version : 2025-11-25 latest spec Transports : stdio, Streamable HTTP, SSE, WebSocket Hot Reload : Capability YAMLs plus reloadable gateway config sections are watched and reloaded live Reload Outcomes : gateway reload config and /ui/api/reload return restart required for listener changes for example server.host / server.port ; env files list edits remain startup-only Config Discovery : Auto-finds gateway.yaml in cwd, ~/.config/mcp-gateway/ , /etc/mcp-gateway/ "Did You Mean?" : Levenshtein-based typo correction on tool names Tool Annotations : MCP 2025-11-25 title , readOnlyHint , destructiveHint , idempotentHint , openWorldHint ; gateway meta-tools are fully annotated, while backend tools use the hybrid pass-through/fill policy in ADR-003 /MikkoParkkola/mcp-gateway/blob/main/docs/adr/ADR-003-mcp-tool-annotation-policy.md Dynamic Descriptions : Live tool/server counts in meta-tool descriptions Tunnel Mode : Expose via Tailscale or pipenet without opening ports Shell Completions : mcp-gateway completions bash|zsh|fish Spec Preview opt-in : Filtered tools/list SEP-1821 , tools/resolve SEP-1862 , dynamic promotion Any MCP-compliant server works. All three transport types supported: | Transport | Examples | |---|---| stdio | @anthropic/mcp-server-tavily , @modelcontextprotocol/server-filesystem , @modelcontextprotocol/server-github | HTTP | Any Streamable HTTP server | SSE | Pieces, LangChain, | Remote MCP servers plug in by URL — no extra code. See examples/gateway-full.yaml /MikkoParkkola/mcp-gateway/blob/main/examples/gateway-full.yaml for a commented GitMCP backend entry and docs/REMOTE BACKENDS.md /MikkoParkkola/mcp-gateway/blob/main/docs/REMOTE BACKENDS.md for a step-by-step walkthrough. | Endpoint | Method | Description | |---|---|---| /health | GET | Health check with backend status | /mcp | POST | Meta-MCP mode dynamic discovery | /mcp/{backend} | POST | Direct backend access | /ui | GET | Web dashboard | /dashboard | GET | Operator dashboard | /metrics | GET | Prometheus metrics with --features metrics | | Metric | Value | Notes | |---|---|---| Startup time | ~8ms | Measured with hyperfine | Binary size | ~12-13 MB | Release build with LTO, stripped | Hot-path microbenchmarks | Included | Criterion suite covers registry, parsing, cache-key, firewall, and semantic search hot paths | End-to-end latency | Backend-dependent | Measure with your real MCP servers and REST APIs rather than relying on a synthetic single number | MCP Gateway can ingest Agent Skills https://agentskills.io / Claude Code SKILL.md files and expose them as discoverable skills alongside capability YAML. This lets the gateway consume any SKILL.md — whether authored locally, shipped from agentskills.io , or pulled from a GitHub release — and surface it through the same meta-tool surface used for capabilities. Import a local skill directory auto-discovers SKILL.md + resources/ mcp-gateway skills import ~/.claude/skills/gws-gmail-send Import a single SKILL.md file mcp-gateway skills import ./path/to/SKILL.md Import from an agentskills.io URL mcp-gateway skills import https://agentskills.io/skills/my-skill/SKILL.md List imported skills mcp-gateway skills list Search by name, description, trigger, or keyword mcp-gateway skills search "gmail" Show the full body including any embedded code blocks mcp-gateway skills show gws-gmail-send Remove a skill mcp-gateway skills remove gws-gmail-send What gets parsed - YAML frontmatter name , description , version , effort , allowed-tools , triggers , keywords - Markdown body, with fenced bash / python / json code blocks extracted as structured SkillCodeBlock entries - Progressive-disclosure resources: SKILL.advanced.md , reference.md , README.md , and any resources/ .md files in the skill directory Security model read-only Imported skills are stored as data, not executed. Embedded bash or python blocks are parsed and surfaced to users/agents via skills show , but MCP Gateway will never run them automatically. A future release may add opt-in execution gated on per-skill user consent. If you need to run a skill's commands today, copy them from skills show and run them in your own shell. Registry location: ~/.mcp-gateway/skills.json override with MCP GATEWAY SKILLS REGISTRY or --registry . Reference: Anthropic SKILL.md spec https://docs.claude.com/en/docs/claude-code/skills · agentskills.io https://agentskills.io | Document | Contents | |---|---| | Configuration Reference /MikkoParkkola/mcp-gateway/blob/main/docs/QUICKSTART.md configuration OAuth Configuration /MikkoParkkola/mcp-gateway/blob/main/docs/OAUTH CONFIG.md Deployment Guide /MikkoParkkola/mcp-gateway/blob/main/docs/DEPLOYMENT.md OpenAPI Import /MikkoParkkola/mcp-gateway/blob/main/docs/OPENAPI IMPORT.md Webhooks /MikkoParkkola/mcp-gateway/blob/main/docs/WEBHOOKS.md Community Registry /MikkoParkkola/mcp-gateway/blob/main/docs/COMMUNITY REGISTRY.md Benchmarks /MikkoParkkola/mcp-gateway/blob/main/docs/BENCHMARKS.md Changelog /MikkoParkkola/mcp-gateway/blob/main/CHANGELOG.md OWASP Agentic AI Compliance /MikkoParkkola/mcp-gateway/blob/main/docs/OWASP AGENTIC AI COMPLIANCE.md vs Anthropic MCP Tunnels vs-anthropic-mcp-tunnels Backend won't connect? Test the command directly npx -y @anthropic/mcp-server-tavily , then check gateway logs with --log-level debug . Circuit breaker open? Check curl localhost:39400/health | jq '.backends' . Adjust thresholds in failsafe.circuit breaker . Tools not appearing? Verify the backend is running gateway list servers . Tool lists are cached for 5 minutes. - Fork and branch git checkout -b feature/your-feature - Test cargo test and lint cargo fmt && cargo clippy -- -D warnings - PR against main with a clear description and CHANGELOG /MikkoParkkola/mcp-gateway/blob/main/CHANGELOG.md entry See CONTRIBUTING.md /MikkoParkkola/mcp-gateway/blob/main/CONTRIBUTING.md for full details. Look for good first issue https://github.com/MikkoParkkola/mcp-gateway/labels/good%20first%20issue or to get started. https://github.com/MikkoParkkola/mcp-gateway/labels/help%20wanted help wanted mcp-gateway is part of a suite of MCP tools: | Tool | Description | |---|---| | Universal MCP gateway — compact 13-16 tool surface replaces 100+ registrations | | nab https://github.com/MikkoParkkola/nab axterminator https://github.com/MikkoParkkola/axterminator mcp-gateway is dual-licensed as of v2.11.0: | Scope | License | File | |---|---|---| | Core gateway, capabilities, transport, CLI, and everything not listed below | MIT | | LICENSE-EE.md /MikkoParkkola/mcp-gateway/blob/main/LICENSE-EE.md EE-designated paths every file carries // SPDX-License-Identifier: PolyForm-Noncommercial-1.0.0 : src/security/firewall/ — egress filtering src/security/agent identity.rs — identity-based access control OWASP ASI03 src/security/data flow.rs — data flow tracking EU AI Act Art. 12 src/security/message signing.rs — HMAC inter-agent signing OWASP ASI07 src/security/policy.rs — advanced policy enforcement src/security/response inspect.rs , response scanner.rs — outbound credential / exfil detection src/security/scope collision.rs — scope conflict detection src/security/tool integrity.rs — tool poisoning detection OWASP ASI04 src/cost accounting/ — cost governance src/key server/ — OIDC-backed scoped key issuance What this means in practice : - Free for noncommercial use, modification, redistribution. - Commercial use of EE modules requires a separate commercial license. - Companies can buy a standard commercial-use license via GitHub Sponsors https://github.com/sponsors/MikkoParkkola at EUR 500/month per named project. - See COMMERCIAL.md /MikkoParkkola/mcp-gateway/blob/main/COMMERCIAL.md for business use, forks, wrappers, shared services, and managed-service deployments. - All releases prior to v2.11.0 remain entirely MIT and stay MIT forever. Created by Mikko Parkkola https://github.com/MikkoParkkola . Implements Model Context Protocol https://modelcontextprotocol.io/ version 2025-11-25.