IBM Context Forge MCP — Сценарии использования, Установка & Живое демо

Name: IBM Context Forge MCP Server
Author: IBM

Зачем использовать

Ключевые функции

Federate multiple MCP servers behind one endpoint
Translate REST and gRPC APIs into MCP tools automatically
Built-in JWT / OAuth / Basic auth, rate limiting, retries
OpenTelemetry tracing (Phoenix, Jaeger, Zipkin) + admin UI

Живое демо

Как выглядит на практике

mcp-context-forge.replay ▶ готово

0/0

Установка

Выберите клиент

~/Library/Application Support/Claude/claude_desktop_config.json · Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "mcp-context-forge": {
      "command": "uvx",
      "args": [
        "mcp-context-forge"
      ]
    }
  }
}

Откройте Claude Desktop → Settings → Developer → Edit Config. Перезапустите после сохранения.

~/.cursor/mcp.json · .cursor/mcp.json

{
  "mcpServers": {
    "mcp-context-forge": {
      "command": "uvx",
      "args": [
        "mcp-context-forge"
      ]
    }
  }
}

Cursor использует ту же схему mcpServers, что и Claude Desktop. Конфиг проекта приоритетнее глобального.

VS Code → Cline → MCP Servers → Edit

{
  "mcpServers": {
    "mcp-context-forge": {
      "command": "uvx",
      "args": [
        "mcp-context-forge"
      ]
    }
  }
}

Щёлкните значок MCP Servers на боковой панели Cline, затем "Edit Configuration".

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "mcp-context-forge": {
      "command": "uvx",
      "args": [
        "mcp-context-forge"
      ]
    }
  }
}

Тот же формат, что и Claude Desktop. Перезапустите Windsurf для применения.

~/.continue/config.json

{
  "mcpServers": [
    {
      "name": "mcp-context-forge",
      "command": "uvx",
      "args": [
        "mcp-context-forge"
      ]
    }
  ]
}

Continue использует массив объектов серверов, а не map.

~/.config/zed/settings.json

{
  "context_servers": {
    "mcp-context-forge": {
      "command": {
        "path": "uvx",
        "args": [
          "mcp-context-forge"
        ]
      }
    }
  }
}

Добавьте в context_servers. Zed перезагружается автоматически.

claude mcp add mcp-context-forge -- uvx mcp-context-forge

Однострочная команда. Проверить: claude mcp list. Удалить: claude mcp remove.

Сценарии использования

Реальные сценарии: IBM Context Forge

Centralize 10+ MCP servers behind one gateway

👤 Platform engineers at mid/large orgs ⏱ ~120 min advanced

Когда использовать: Different teams run different MCPs. You need one URL for clients, one audit log, one auth story.

Предварительные требования

Docker/Kubernetes environment — Official images at ghcr.io; Helm chart available
An auth provider (or use built-in JWT) — Existing SSO / OIDC / static JWT signer

Поток

Deploy the gateway

Deploy mcp-contextforge-gateway via Helm with Redis for federation state. Point it at our OIDC provider.✓ Скопировано

→ Admin UI loads, auth works
Register backends

Register 3 backend MCPs (github, postgres, our-custom) in the admin UI. Apply rate limits: github=100/min, postgres=30/min.✓ Скопировано

→ Backends appear as healthy in registry
Repoint clients

Update teammate Claude Desktop configs to use a single mcp-remote https://mcp-gw.company.com/mcp with their JWT.✓ Скопировано

→ All backend tools available through one connection

Итог: One place to manage MCP access across the org — centralized like any other API gateway.

Подводные камни

Rate limits applied globally but teams have different needs — Use per-user or per-JWT-claim rate limits via the policy engine — don't apply one limit to all
Gateway becomes single point of failure — Run at least 2 replicas with Redis-backed session state; health-check the /health endpoint

Сочетать с: cloud-run

Virtualize a REST API as MCP without writing a server

👤 Platform engineers without Python/TS bandwidth ⏱ ~60 min intermediate

Когда использовать: You have an internal REST API with an OpenAPI spec. You want MCP access without writing fastapi-mcp or FastMCP code.

Предварительные требования

OpenAPI / Swagger spec for the API — Usually /openapi.json or /swagger.json

Поток

Upload the OpenAPI spec

In ContextForge admin, register a new REST backend. Upload the OpenAPI spec. Confirm tool auto-generation picked up all endpoints.✓ Скопировано

→ Tool list matches route list
Configure auth passthrough

Set up header forwarding so the Authorization header flows from the MCP client to the upstream REST API.✓ Скопировано

→ Authenticated routes work end-to-end
Filter exposed surface

Exclude internal/admin routes via path patterns. Add a description override on the 3 most-used tools.✓ Скопировано

→ Clean, agent-friendly tool list

Итог: REST-as-MCP with zero new service code — an OpenAPI spec is enough.

Подводные камни

Auto-generated tool names are awful — Set explicit operationIds in your OpenAPI spec or override names in ContextForge per route

Add tracing and analytics to all MCP calls across your org

👤 SRE / platform observability leads ⏱ ~90 min advanced

Когда использовать: You want to answer 'what did the agents do today?' across every team using MCP.

Предварительные требования

An OTel backend (Phoenix, Jaeger, Grafana Tempo) — Running endpoint that accepts OTLP

Поток

Enable OTel export

Configure the gateway's otel.endpoint to point at our Phoenix instance. Include tool name, latency, user, outcome in spans.✓ Скопировано

→ Spans appear in Phoenix within seconds of calls
Build dashboards

Create dashboards: top 10 tools by call volume, p95 latency per backend, error rates per user.✓ Скопировано

→ Dashboards populated
Alert on anomalies

Alert on: error rate >5% for any backend, or a single user burning >10k calls/hour.✓ Скопировано

→ Test alerts fire in staging

Итог: Org-wide MCP visibility — you know who uses what and when it breaks.

Подводные камни

OTel span cardinality explodes with per-request IDs as span names — Keep span names to tool names; put request IDs in attributes, not names

Сочетать с: sentry

Комбинации

Сочетайте с другими MCP — эффект x10

mcp-context-forge + cloud-run

Deploy ContextForge on Cloud Run, federate GCP-hosted MCPs behind it

Deploy ContextForge to Cloud Run with IAM auth. Register our 3 internal MCPs (also on Cloud Run) as backends.✓ Скопировано

mcp-context-forge + sentry

Ship gateway traces + errors to Sentry for ops visibility

Configure the gateway's OTel export to also push errors into Sentry for on-call visibility.✓ Скопировано

Инструменты

Что предоставляет этот MCP

Инструмент	Входные данные	Когда вызывать	Стоимость
Gateway federation	N registered backends	Infra-level; not a per-request tool	free
REST → MCP virtualization	OpenAPI spec + target URL	Onboarding a REST service to MCP	passthrough of target API costs
gRPC → MCP translation	gRPC service descriptor	Same as above, for gRPC backends	passthrough
Prompt registry	Jinja2 templates + variables	Share prompts across teams with versioning	free
Resource registry	URI-based resources	Expose static/ dynamic org content	free
Admin API / UI	HTTP + web UI	Ops/config tasks	free

Стоимость и лимиты

Во что обходится

Квота API: Self-hosted — whatever your infra supports
Токенов на вызов: Gateway adds ~50ms + minimal schema overhead
Деньги: Open source (Apache 2.0); you pay for infra + backends
Совет: Start with SQLite backend for <10 servers; only move to Redis federation when you need multi-node HA

Безопасность

Права, секреты, радиус поражения

Хранение учётных данных: JWT signing keys in secret manager; never in env vars on container images

Исходящий трафик: Gateway → all configured backends; OTel → tracing backend

Active project — pin the version in your Helm values and review release notes before upgrading

Устранение неполадок

Частые ошибки и исправления

Backend marked unhealthy but works when tested directly

Health checks use HEAD or GET /; your backend may only respond to POST. Configure health_check.path per backend.

JWT validation fails

Check iss and aud claims match gateway config. Also verify the JWKS endpoint is reachable from the gateway pod.

Rate limit too aggressive during spikes

Switch from fixed-window to token-bucket policy; set burst=5× average.

Admin UI login loops

Redirect URI in your OIDC provider must match /auth/callback on the gateway's external URL — verify it's set for the exact public hostname.

Альтернативы

IBM Context Forge в сравнении

Альтернатива	Когда использовать	Компромисс
Kong / Apigee + custom plugins	You already run these and want to extend rather than add a new gateway	Needs plugin development; MCP not first-class
mcp-use server namespace	Single-developer use case — just wire multiple MCPs client-side	No central governance; fine for individuals not orgs
Cloudflare AI Gateway	You want a hosted SaaS gateway, not self-hosted	Less MCP-specific functionality; primarily LLM traffic focus

Ещё

Ресурсы

📖 Читать официальный README на GitHub

🐙 Открытые задачи

🔍 Все 400+ MCP-серверов и Skills