{"slug": "manage-mcp-context-with-postman-fabric-gateway", "title": "Manage MCP context with Postman Fabric Gateway", "summary": "Postman published a tutorial showing how to connect multiple Model Context Protocol (MCP) servers through a single Postman Fabric Gateway endpoint and enable progressive tool discovery, so agents retrieve tool schemas on demand instead of loading every definition upfront. The walkthrough connects a banking MCP server and a support MCP server, stores their bearer credentials in Fabric Gateway's secure vault, and exposes them on the routes /banking/mcp and /support/mcp before combining the catalogs into one route. Postman frames the approach as a way for enterprise teams to cut token waste from irrelevant schemas while controlling access, credentials, and tool execution.", "body_md": "# Manage MCP context with Postman Fabric Gateway\n\nThe Model Context Protocol (MCP) helps agentic systems act on and retrieve information from external tools. As applications grow, agents may need to work across many MCP servers and large tool catalogs, making context management harder.\n\nLoading every tool definition upfront wastes tokens on irrelevant schemas and leaves less room for instructions, history, and task data. At enterprise scale, teams need a deliberate way for agents to discover relevant tools while controlling access, credentials, and tool execution.\n\nIn this tutorial, we’ll show how to use [Postman Fabric Gateway](https://app.fabricgateway.ai/) to connect multiple MCP servers through a single endpoint and enable progressive tool search so agents can retrieve tool schemas only when needed.\n\nPrefer to watch? This tutorial is also available as a video walkthrough:\n\n[https://www.youtube.com/watch?v=vhyfXyXM9Vc](https://www.youtube.com/watch?v=vhyfXyXM9Vc)\n\n## What You’ll Learn\n\nBy the end of this tutorial, you’ll know how to:\n\n- Connect multiple MCP servers to Postman Fabric Gateway and manage their upstream credentials securely.\n- Create individual and combined routes so clients can access multiple tool catalogs through a single MCP endpoint.\n- Enable progressive tool discovery so agents can search for relevant tools, retrieve schemas on demand, and execute tools without loading the full catalog upfront.\n\n## Pre-requisites\n\nYou’ll need the following before you start:\n\n- A [Fabric Gateway account](https://app.fabricgateway.ai/)\n- A [Postman account](https://postman.com) with access to the workspace where you’ll test the integration.\n- A basic understanding of MCP\n\nIn this tutorial, we are going to work with two MCP servers. A support MCP server and a banking MCP server. These MCP servers are used by a support agent to manage customer transaction disputes. We won’t go into the technicalities of the agent or the tools that the MCP server exposes.\n\n## Step 1: Connect the MCP servers and configure their credentials\n\nIn Fabric Gateway, click on **MCP servers** in the left navigation menu, and select **Create connection**.\n\nName the connection `banking-mcp` and enter the below URL as the banking server’s full MCP endpoint.\n\nIn the **Upstream auth requirement**, select **Bearer** auth type and toggle the radio box.\n\nNext, you need to provide the required authorization credential to Fabric Gateway.\n\nCopy and paste `banking-mcp-demo-key` as the API key into the token input box.\n\nThis will create a service level credential for the connection. This credential will be stored in a secure vault.\n\nThis setup screen allows you to create a connection, and expose that connection on a newly created route in one go. Fill in a preferred name for the new route, and provide a path that you want it exposed on. Toggle the “Gateway Key” option and select “No gateway key”.\n\nSave the connection by clicking on **Create Connection**.\n\nRepeat this process for the `support-mcp` connection.\n\n| Connection Name | Upstream URL | Credential/API Key | \n|---|---|---|\n| `banking-mcp` | `https://intergalacticbanking-mcp-production.up.railway.app/mcp` | **Banking MCP Key** :`banking-mcp-demo-key` | \n| `support-mcp` | `https://intergalacticsupport-mcp-production.up.railway.app/mcp` | **Support MCP Key** :`support-mcp-demo-key` | \n\n## Step 2: Create a route to combine the tool catalogs\n\nCreating a connection tells Fabric where a service lives. A route gives clients an endpoint through which to use it. You’ve created a route for each service so you can test them independently.\n\n| Route path | Connected service | \n|---|---|\n| `/banking/mcp` | Banking MCP | \n| `/support/mcp` | Support MCP | \n\nNavigate to MCP Servers on the left sidebar. Switch to the **routes** tab and click on the **Copy DP URL** icon to the right of any of the routes.\n\nIn Postman, create an MCP request, and paste the DP URL you just copied. Test any of the MCP tools in the tool list.\n\nRepeat this process for both MCP servers.\n\nNext, we want to be able to combine these two MCP server tools on a single route. Still on the routes tab, click on **“Create Route”** to create a third route.\n\nName this route `all-mcp`, give it a path such as `/banking/all`, and select **both** services.\n\nCopy the DP URL, and send an MCP request to it in Postman.\n\nThe client now lists tools from both servers through one endpoint. Fabric prefixes and namespaces the tool names so you can identify each tool’s originating service; in this setup, the combined list contains 103 tools.\n\nWe’ve consolidated the connection, but the client still receives the full catalog. The next step changes that.\n\n## Step 3: Enable progressive tool discovery\n\nOpen **Plugin**, scroll down, and click on **Use** on the **Tool Search** option. Give this plugin a name and scope it to the **all-mcp** route you just created.\n\nClick on the **Edit as JSON** button and paste the below JSON. Switch back to form mode and confirm that the openai service is indeed selected, then save.\n\n**NOTE:** You can use any embedding model or service of your choosing here\n\nThis plugin introduces an embedding service that makes it possible to search a tool catalog semantically. This means a request such as “list transactions” can return relevant tools without requiring their exact names. This is explained in more detail shortly.\n\nDisconnect and reconnect the combined MCP request in Postman to refresh its tool listing.\n\nInstead of 103 tool definitions, you should now see three tools that perform these jobs:\n\n| Capability | Purpose | \n|---|---|\n| Search tools | Find relevant tools across the catalog using a natural-language query. This uses the added embedded service in tool search. | \n| Get tool | Retrieve the selected tool’s definition, including its input schema. | \n| Execute tool | Invoke the selected tool with the required arguments. | \n\nThis means that the Agent can now progressively discover tools rather than load the entire tool schema upfront. The upstream tools have not been deleted or merged into three operations. Instead, the gateway has changed how the client discovers and invokes them.\n\nTest discovery with a simple query: **“list transactions.”** Run the search tool and review the returned matches. You should see candidates relevant to transaction lookup, rather than the complete banking and support tool catalog.\n\nCopy the name of one of the returned tools e.g `ban__banking_list_transactions`, and paste that name into the get_tool tool to retrieve the schema definitions of that tool. Then use the execute-tool capability with that tool’s identifier and arguments.\n\nThis is the sequence an agent will follow: find a relevant capability, learn how to call it, then act. In the Postman MCP Client, you just walked through each stage manually.\n\n## Step 4: Monitor Traces and telemetry\n\nFabric Gateway automatically collects telemetry across all services and routes. You can view the traces on the Gateway’s dashboard. Click on traces in the left sidebar. This should show you a list of all the requests that have been routed by the Gateway, and you can click on any of them to view the end-to-end trace.\n\nTraces let you examine route matching, plugin execution, and upstream activity where applicable.\n\nThis is useful when a call fails: you can investigate what happened at the gateway instead of relying only on the error shown by the client.\n\n## What changes for the agent\n\nIn this tutorial, we showed how to expose multiple MCP servers through a single MCP endpoint, reduce an agent’s tool surface area, and provide a focused set of tools that are easier for an agent to discover and use.\n\nThe result is one MCP endpoint backed by two services, with three tools initially listed instead of 103. That gives a smaller starting point for an application that would otherwise pass the complete catalog to its model. It is **not** a measured percentage reduction in tokens or cost: search results, retrieved schemas, and tool responses still consume context, and discovery adds requests. Measure the full workflow when comparing performance.\n\nThe practical benefit is control over when tool definitions enter the conversation. The agent can request the capability it needs, while the gateway manages credentials, enforces access policies, and inspects traffic.\n\n## Resources\n\n- Sign in to [Fabric Gateway](https://app.fabricgateway.ai/) and configure MCP services, routes, credentials, plugins, and traces.\n- Read the [Fabric Gateway documentation](https://docs.fabricgateway.ai/get-started/overview/) .\n- [Learn how to create and test MCP requests in Postman](https://learning.postman.com/latest-v-12/docs/use/send-requests/protocols/mcp-requests/create) .\n\n*This was originally posted on [fabricgateway.ai/blog](https://fabricgateway.ai/blog/manage-mcp-context-with-postman-fabric-gateway/)*", "url": "https://wpnews.pro/news/manage-mcp-context-with-postman-fabric-gateway", "canonical_source": "https://blog.postman.com/postman-fabric-gateway-connect-multiple-mcp-servers/", "published_at": "2026-11-02 17:11:20+00:00", "updated_at": "2026-11-02 17:20:15.582602+00:00", "lang": "en", "topics": ["ai-agents", "agent-protocols", "ai-tools", "developer-tools"], "entities": ["Postman", "Postman Fabric Gateway", "Model Context Protocol", "banking-mcp", "support-mcp"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/manage-mcp-context-with-postman-fabric-gateway", "markdown": "https://wpnews.pro/news/manage-mcp-context-with-postman-fabric-gateway.md", "text": "https://wpnews.pro/news/manage-mcp-context-with-postman-fabric-gateway.txt", "jsonld": "https://wpnews.pro/news/manage-mcp-context-with-postman-fabric-gateway.jsonld"}}