--- title: "Context Graph | Postman API Platform" description: "A continuously updated graph of every API, deployment, and dependency you own, so agents can answer \"what breaks if I change this?\" before they write the code." url: https://www.postman.com/context-graph/?utm_source=www-next-llm --- # Context Graph | Postman API Platform > A continuously updated graph of every API, deployment, and dependency you own, so agents can answer "what breaks if I change this?" before they write the code. ## Context Graph API Give your agents an authenticated, connected view of API and service relationships. Trace downstream impact, identify affected consumers, and catch breaking changes before you merge every line of code. --- ## One graph, built from everywhere your APIs actually live ### Connect what you already have Your Postman workspaces, your GitHub repos, and your running services in New Relic. Connect once. ### Every edge shows its work Typed nodes, six typed edges, and evidence on each one: the commit it was seen at, and where the signal came from. ### Answer impactful questions to accelerate your agentic SDLC Blast radius, dependency chains, endpoint consumers, ownership. --- ## How Context Graph works --- *CAPABILITIES* ### Answer questions single repo or search tools can't Context Graph helps expand your coding agent's abilities beyond your codebase: across service boundaries, across repos, across environments. ### Blast radius across repos "If I change this endpoint, which services break?" Callers usually live in other repositories, often with no greppable path. The graph already stores that edge, so nobody has to rebuild it from scratch. ### Dependency chains and cycles Walk upstream and downstream between deployments, find the shortest path between two services, and surface dependency cycles before they become an incident. ### Ownership and what's really running Every API carries its owning team and its deployments. Connecting New Relic adds what is actually running and when it was last observed. That signal exists in no repository at all. --- *ASK IT ANYTHING* You ask in plain language. These are the kinds of questions it answers across your whole estate. ### What breaks if I change this endpoint? ### Which services depend on this API? ### Who actually calls this endpoint? ### What are our most-depended-on services and stubs? --- ## Benchmarked across an estate of 468 repositories Eight questions, three models, three runs of each arm. Same model, same questions, same tools, with and without the graph. _Source: September 2026 benchmarking: 468 repositories, three models, 144 runs. Cost excludes the one-time graph build and ongoing re-ingestion._ **29%** fewer prompt tokens **17%** fewer tool calls per run **27%** lower cost per run --- ### Fewer tokens on the questions that span systems **Reduction in prompt tokens when the model queries the graph before it reads any code**, Opus 4.7 over 468 repositories. These are the three largest reductions of the eight questions we asked. The savings come from fewer round trips: 57 tool calls per question instead of 69. --- ## GETTING STARTED Try Context Graph directly in Postman with a pre-built ask against the live API. 1. Context Graph is authenticated, so sign in to your Postman account before running queries. 2. [Add a Postman API key](https://learning.postman.com/docs/reference/postman-api/authentication?utm_source=www-next-llm) in the request's **Authorization** tab. 3. Set the active **environment** to _Context Graph API_. 4. Each graph is populated per team, so whichever team you're signed in as is the team whose nodes get ingested and queried. 5. Edit the query in the request **body** to ask your own question. You can also view your ingested graph any time from the Postman home button → **Agent Context**. [Query the Context Graph](https://www.postman.com/postman/postman-context-graph-api/http-request/jhcu2uf/submit-a-context-graph-ask?sideView=agentMode&utm_source=www-next-llm) --- ## USE IT FROM YOUR CODING AGENT Reach the same graph whichever way your agent works: from the CLI, through MCP, or over HTTP. **CLI + skills.** Run postman init in your repo to install Postman's agent skills, then your coding agent queries the graph through the Postman CLI, with no HTTP wiring or polling to manage. **MCP.** Point any MCP client at https://mcp.postman.com/context-graph, or add the --context-graph toolset to the Postman MCP server, and the graph shows up as a tool. **HTTP.** Call the Context Graph API directly with a Postman API key: submit an ask and poll for the result. [Add the Postman CLI](/product/postman-cli/?utm_source=www-next-llm) --- ## See how the Context Graph helps with a multi-repo change [See a multi-repo change](https://blog.postman.com/multi-repo-api-changes-with-the-postman-ai-engineer/?utm_source=www-next-llm) --- *RESOURCES* ## Go deeper on Context Graph ### Steer Your Agents Until They Steer Themselves How we built an AI agent platform for enterprise GTM: deployments each team can steer, measured improvement, and evals for non-verifiable domains. [Read the post](https://blog.postman.com/steer-your-agents-until-they-steer-themselves/?utm_source=www-next-llm) ### Agentic SDLC with the Claude Code Plugin Watch Claude Code use Postman's Context Graph to sync a collection, verify a contract, and wire CI. Try the workflow on your own API. [Read the post](https://blog.postman.com/agentic-sdlc-with-the-claude-code-plugin/?utm_source=www-next-llm) ### Postman adds site-wide licensing, Private Cloud, and an air-gapped client Learn how Postman's new site-wide licensing, Private Cloud, and air-gapped client help enterprises control deployment and secure API access for agents. [Read the post](https://blog.postman.com/postman-adds-site-wide-licensing-private-cloud-and-an-air-gapped-client/?utm_source=www-next-llm) --- ### Frequently asked questions ### What is Postman Context Graph? A continuously updated graph of your API estate. It ingests your Postman workspaces, code repositories, and runtime telemetry, then turns them into typed entities (APIs, endpoints, deployments, databases, teams) joined by typed relationships. Agents query that graph instead of reconstructing it from whatever files are open. ### Which sources can Context Graph ingest? Your Postman workspaces are the primary source: the specs, collections, and environments your teams already maintain. Beyond that, GitHub repositories scanned for OpenAPI, AsyncAPI, and service definitions, and New Relic for the deployments and telemetry a code scan cannot see. ### How does the graph stay current? Each source carries its own policy: a refresh interval, a webhook, or manual. Re-ingestion is incremental, so unchanged repositories are skipped and cost tracks your code churn rather than your estate size. Runtime connectors stream continuously. ### What does Context Graph know about an API? What it exposes, calls, and depends on at runtime. Which databases back it, which external services it talks to, which team owns it, where it is deployed, and what watches it. Every relationship carries its evidence, so you can tell a confirmed edge from an inferred one. ### Can I use Context Graph through MCP? Yes. Point any MCP client you already run (your editor, your agent framework, your own harness) at https://mcp.postman.com/context-graph, or add the --context-graph toolset to the [Postman MCP server](/product/mcp-server/?utm_source=www-next-llm), and the graph is available as a tool, without writing the HTTP request or handling the asynchronous polling yourself. The HTTP endpoint is still available for anything you'd rather build against directly. ### When should I not use the graph? When the answer is already in the files in front of you. Our benchmarking found that on a declared dependency, like who imports a module, go.mod answers outright: reading the repository scores 98% on its own and the graph adds nothing. It earns its keep on cross-boundary work. ### Is Context Graph available today? Yes, [try it now](https://www.postman.com/postman/workspace/postman-context-graph-api?utm_source=www-next-llm).