IBM Context Forge MCP — 사용 사례, 설치 & 라이브 데모

Name: IBM Context Forge MCP Server
Author: IBM

왜 쓰나요

핵심 기능

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

라이브 데모

실제 사용 모습

mcp-context-forge.replay ▶ 준비됨

0/0

설치

클라이언트 선택

~/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"
      ]
    }
  }
}

Claude Desktop → Settings → Developer → Edit Config 열기. 저장 후 앱 재시작.

~/.cursor/mcp.json · .cursor/mcp.json

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

Cursor는 Claude Desktop과 동일한 mcpServers 스키마 사용. 프로젝트 설정이 전역보다 우선.

VS Code → Cline → MCP Servers → Edit

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

Cline 사이드바의 MCP Servers 아이콘 클릭 후 "Edit Configuration" 선택.

~/.codeium/windsurf/mcp_config.json

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

Claude Desktop과 같은 형식. Windsurf 재시작 후 적용.

~/.continue/config.json

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

Continue는 맵이 아닌 서버 오브젝트 배열 사용.

~/.config/zed/settings.json

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

context_servers에 추가. 저장 시 Zed가 핫 리로드.

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

한 줄 명령. claude mcp list로 확인, claude mcp remove로 제거.

사용 사례

실전 활용법: IBM Context Forge

Centralize 10+ MCP servers behind one gateway

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

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

사전 조건

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

흐름

Deploy the gateway

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

→ 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.✓ 복사됨

→ 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.✓ 복사됨

→ All backend tools available through one connection

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

함정

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

함께 쓰기: cloud-run

Virtualize a REST API as MCP without writing a server

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

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

사전 조건

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

흐름

Upload the OpenAPI spec

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

→ 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.✓ 복사됨

→ 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.✓ 복사됨

→ Clean, agent-friendly tool list

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

함정

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

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

사전 조건

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

흐름

Enable OTel export

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

→ 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.✓ 복사됨

→ Dashboards populated
Alert on anomalies

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

→ Test alerts fire in staging

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

함정

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

함께 쓰기: sentry

조합

다른 MCP와 조합해 10배 효율

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.✓ 복사됨

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.✓ 복사됨

도구

이 MCP가 노출하는 것

도구	입력	언제 호출	비용
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

비용 및 제한

운영 비용

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

보안

권한, 시크릿, 파급범위

자격 증명 저장: JWT signing keys in secret manager; never in env vars on container images

데이터 외부 송신: Gateway → all configured backends; OTel → tracing backend

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

문제 해결

자주 발생하는 오류와 해결

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.

대안

IBM Context Forge 다른 것과 비교

대안	언제 쓰나	단점/장점
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

IBM Context Forge

왜 쓰나요

핵심 기능

라이브 데모

실제 사용 모습

설치

클라이언트 선택

사용 사례

실전 활용법: IBM Context Forge

Centralize 10+ MCP servers behind one gateway

사전 조건

흐름

함정

Virtualize a REST API as MCP without writing a server

사전 조건

흐름

함정

Add tracing and analytics to all MCP calls across your org

사전 조건

흐름

함정

조합

다른 MCP와 조합해 10배 효율

도구

이 MCP가 노출하는 것

비용 및 제한

운영 비용

보안

권한, 시크릿, 파급범위

문제 해결

자주 발생하는 오류와 해결

대안

IBM Context Forge 다른 것과 비교

더 보기

리소스