IBM Context Forge MCP — Use Cases, Install & Live Demo

Name: IBM Context Forge MCP Server
Author: IBM

Why use it

Key features

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

Live Demo

What it looks like in practice

mcp-context-forge.replay ▶ ready

0/0

Install

Pick your client

~/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"
      ]
    }
  }
}

Open Claude Desktop → Settings → Developer → Edit Config. Restart after saving.

~/.cursor/mcp.json · .cursor/mcp.json

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

Cursor uses the same mcpServers schema as Claude Desktop. Project config wins over global.

VS Code → Cline → MCP Servers → Edit

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

Click the MCP Servers icon in the Cline sidebar, then "Edit Configuration".

~/.codeium/windsurf/mcp_config.json

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

Same shape as Claude Desktop. Restart Windsurf to pick up changes.

~/.continue/config.json

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

Continue uses an array of server objects rather than a map.

~/.config/zed/settings.json

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

Add to context_servers. Zed hot-reloads on save.

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

One-liner. Verify with claude mcp list. Remove with claude mcp remove.

Use Cases

Real-world ways to use IBM Context Forge

Centralize 10+ MCP servers behind one gateway

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

When to use: Different teams run different MCPs. You need one URL for clients, one audit log, one auth story.

Prerequisites

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

Flow

Deploy the gateway

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

→ 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.✓ Copied

→ 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.✓ Copied

→ All backend tools available through one connection

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

Pitfalls

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

Combine with: cloud-run

Virtualize a REST API as MCP without writing a server

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

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

Prerequisites

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

Flow

Upload the OpenAPI spec

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

→ 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.✓ Copied

→ 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.✓ Copied

→ Clean, agent-friendly tool list

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

Pitfalls

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

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

Prerequisites

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

Flow

Enable OTel export

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

→ 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.✓ Copied

→ Dashboards populated
Alert on anomalies

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

→ Test alerts fire in staging

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

Pitfalls

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

Combine with: sentry

Combinations

Pair with other MCPs for X10 leverage

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.✓ Copied

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.✓ Copied

Tools

What this MCP exposes

Tool	Inputs	When to call	Cost
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

Cost & Limits

What this costs to run

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

Security

Permissions, secrets, blast radius

Credential storage: JWT signing keys in secret manager; never in env vars on container images

Data egress: Gateway → all configured backends; OTel → tracing backend

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

Troubleshooting

Common errors and fixes

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.

Alternatives

IBM Context Forge vs others

Alternative	When to use it instead	Tradeoff
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

More

Resources

📖 Read the official README on GitHub

🐙 Browse open issues

🔍 Browse all 400+ MCP servers and Skills