MCP server

GraphOS MCP Server

io.github.apollographql/graphos-mcp-server

Checked 26 Oct 2026, 08:29 UTC · Connected to it and listed its tools

Search Apollo docs, specs, and best practices

Website

At a glance

Type

MCP server

Publisher

apollographql.com (verified by the MCP Registry)

Status

Working at last check

Tools

48

Token cost

About 17,352 tokens per request

Sets up in

Claude Code, Claude Desktop, Codex, Gemini CLI, Cursor, VS Code, Antigravity, ChatGPT, OpenAI API, Grok

Last checked

26 Oct 2026, 08:29 UTC

Connect it to your agent

Add to CursorAdd to VS CodeVS Code Insiders

Opens the app, which shows the server and asks you to confirm. For other apps, copy the setup below.

Claude Code

claude mcp add --transport http graphos-mcp-server https://mcp.apollographql.com

Claude Desktop

Settings → Connectors → Add custom connector, and paste the URL.

Codex (config.toml)

[mcp_servers.graphos-mcp-server]
url = "https://mcp.apollographql.com"

Gemini CLI

{"mcpServers":{"graphos-mcp-server":{"httpUrl":"https://mcp.apollographql.com"}}}

Cursor

{"mcpServers":{"graphos-mcp-server":{"url":"https://mcp.apollographql.com"}}}

VS Code

{"servers":{"graphos-mcp-server":{"type":"http","url":"https://mcp.apollographql.com"}}}

Antigravity

agy mcp add graphos-mcp-server https://mcp.apollographql.com

ChatGPT

Settings → Apps & Connectors → Advanced settings: turn on Developer mode, then Create a connector and paste the URL. Which plans can do this varies.

OpenAI API (Responses tools)

{"type":"mcp","server_label":"graphos-mcp-server","server_url":"https://mcp.apollographql.com","require_approval":"always"}

Grok (xAI API tools)

{"type":"mcp","server_label":"graphos-mcp-server","server_url":"https://mcp.apollographql.com"}

Tools

• AddProposalComment ~277 tokens
  Add a comment to a schema proposal, the same action as commenting in GraphOS Studio. With no other options, the comment is a general comment on the proposal. To comment on one change, pass the schema coordinate (for example Query.products) and the subgraph name as schemaScope. To reply, pass the par
• ApolloConnectorsSpec ~64 tokens
  Returns the Apollo Connectors specification for guidance on creating or modifying GraphQL schemas that use @connect or @source.
• ApolloDocsRead ~127 tokens
  Reads an Apollo documentation page by slug in chunks. Use slugs returned by ApolloDocsSearch.
• ApolloDocsSearch ~117 tokens
  Searches official Apollo documentation for GraphQL, GraphOS, Apollo Router, Apollo Client, MCP Server, schema design, deployment, and Connectors. Returns URLs, slugs, and excerpts.
• CreateApiKey Changes accounts · ~962 tokens
  Create an API key for an organization. The response contains the new key's value in token. It is a live credential, so give it to the user to store in a secret manager, and do not repeat it, log it, or pass it to another tool. Which key types you can create depends on how you authenticate. With the
• CreateProposal ~225 tokens
  Create a schema proposal against a source variant, the same action as Create proposal in GraphOS Studio. GraphOS creates a proposal variant that starts as a copy of the source variant's schema, and the proposal starts in DRAFT. Returns the proposal variant's name and the new proposal's ID and status
• DeleteApiKey Deletes data · ~132 tokens
  Delete an API key from an organization, the same write that `rover api-key delete` performs. This cannot be undone, and every client that uses the key stops authenticating. Returns the deleted key's ID. Provide the organization ID and the key ID, which GetApiKeys returns.
• DeleteGraph Deletes data · ~131 tokens
  Delete a graph, the same write that `rover graph delete` performs. This is a soft delete: the data is not removed permanently and Apollo support can restore the graph. Every variant of the graph stops serving, so confirm the graph ID with the user before you call this. Returns null on success. Provi
• DeleteSubgraph Deletes data · ~244 tokens
  Remove a subgraph from a variant and start composition, the same write that `rover subgraph delete` performs. Returns the composition errors that the removal causes. This deletes the subgraph from the variant and can break the running router. Set dryRun to true first: the response then reports the c
• GetApiKeys ~656 tokens
  List the API keys and client-credential pairs of an organization. For each key: its ID, name, type, creation, expiry, last use, revocation time, and the resources it can access. For each client-credential pair (an OAuth client that authenticates with the client credentials grant): its client ID, nam
• GetCheckResults ~488 tokens
  Read the outcome of one schema check run: the overall status, and for each task in the run the composition errors, lint diagnostics, schema changes with the client operations they affect, downstream variant results, and custom check violations. Use this after GetSchemaChecks gives you a check ID. Pr
• GetClientMetrics ~1315 tokens
  Traffic broken down by client for a graph over a time window, as compact CSV. Columns: start timestamp, end exclusive timestamp, client name, client version, operation name, request count, request latency p50 ms, request latency p99 ms, request with error count. Answers which clients call a graph, w
• GetContractConfig ~248 tokens
  Read the filter configuration of a contract variant: the tags it includes, the tags it excludes, the source variant it is built from, and a human-readable description of the configuration. This is the same read that `rover contract describe` performs. A contract variant is a filtered view of another
• GetGraphArtifact ~250 tokens
  Fetch a graph artifact by its digest, the same lookup that `rover graph-artifact fetch --digest` performs. A graph artifact is the build output, such as the composed supergraph schema, that GraphOS Router fetches from Apollo's OCI registry. Returns the artifact's ID, digest, status (GRAPH_ARTIFACT_C
• GetGraphArtifactTags ~339 tokens
  List the graph artifact tags on a graph and the artifact each tag points to: the artifact's ID, digest, status, creation time, and variant. GraphOS Router can fetch an artifact by tag name instead of by digest. It is similar to `rover graph-artifact list-tags`, which filters by artifact digest inste
• GetGraphSchema ~201 tokens
  Read the schema (SDL) that is currently published to a graph variant, with its hash and publication time. This is the same read that `rover graph fetch` performs. The response holds the whole document and is not truncated. A large federated graph measured over 800,000 characters, roughly 200,000 tok
• GetLatestLaunch ~168 tokens
  Inspect the most recent launch for a graph variant: status, completion time, subgraph changes, composition errors, and a schema diff summary vs the previous launch (additions/removals/edits/deprecations plus affected operations). Use to assess schema composition health and the impact of recent schem
• GetLaunch ~150 tokens
  Inspect a single launch by ID for full detail: status, timestamps, which subgraphs changed, composition errors, and the schema diff summary. Use to drill into a specific launch — e.g. a failed or superseded one found via GetLaunchHistory (pass its id here). Provide the graph ID, variant name, and la
• GetLaunchHistory ~210 tokens
  Retrieve recent launches for a graph variant (most recent first) to detect deployment instability such as repeated failures or frequent superseded launches. Each entry includes the launch id, status, and timestamps, so you can identify a specific launch and drill into it with GetLaunch. Use to asses
• GetLintResults ~151 tokens
  Retrieve schema lint violations from a graph's most recent schema checks: each diagnostic's coordinate, severity level, message, rule, and source location, plus error/warning/total/ignored counts. Use to assess schema quality and naming/best-practice violations. Provide the graph ID and optionally a
• GetMyIdentity ~212 tokens
  Resolve the caller's identity from their API key or OAuth token. Call this FIRST when the user asks about "my graph" but has not provided a graph ID. For a graph/service key, `me` resolves to a Graph: use `id` as the graphId and `variants[].name` as the variant for the graph-scoped health-check tool
• GetOfflineLicense ~151 tokens
  Fetch the offline Enterprise license for the organization that owns a graph, the same data that `rover license fetch` returns. The license is a signed JWT that lets GraphOS Router enable Enterprise features while it runs disconnected from GraphOS. Returns null when the organization does not have off
• GetOperationMetrics ~1350 tokens
  Top operations by usage/health for a graph over a time window, as compact CSV. Columns: start timestamp, end exclusive timestamp, operation name, request count, request latency p50 ms, request latency p99 ms, request with error count. Ranked by `orderBy` descending: default REQUEST_COUNT (busiest);
• GetPersistedQueryListStatus ~145 tokens
  Check whether a graph variant has a Persisted Query List (PQL), and return its ID, its name, and its current build (revision and operation count). Pass the ID to PublishPersistedQueries. Use to assess PQL configuration — a production variant with no PQL is a security gap. Provide the graph ID and va
• GetProposal ~226 tokens
  Read one schema proposal by its ID: title, description, status, author, the source variant, and the proposal variant with the ID of its latest launch. Also returns the latest revision (its ID, summary, schema check, and launch), every review with its decision and comment, and whether the source vari
• GetProposals ~371 tokens
  List the schema proposals on a graph: each proposal's ID, title, status (DRAFT, OPEN, APPROVED, IMPLEMENTED, CLOSED), timestamps, author, the source variant it proposes changes to, and the proposal variant that holds its changes, plus the total count for the filter. A schema proposal is a reviewable
• GetReadme ~129 tokens
  Read the README of a graph variant, with the time it was last updated and who updated it. This is the same read that `rover readme fetch` performs. The README is the Markdown document shown on the variant's page in GraphOS Studio. Provide the graph ID and the variant name.
• GetSchemaChecks ~428 tokens
  List past schema checks for a graph: each check's ID, status, timestamps, the subgraph it checked, the variant it ran against, the commit, and the status of each task in the check, plus the total count for the filter. Use this to find a check, then pass its ID to GetCheckResults for failure details.
• GetSubgraphMetrics ~1613 tokens
  Top subgraphs/connectors by traffic/health for a graph over a time window, as compact CSV. Columns: start timestamp, end exclusive timestamp, fetch service name, fetch count, fetch latency p50 ms, fetch latency p99 ms, fetch with errors count. Ranked by `orderBy` descending: default FETCH_COUNT (bus
• GetSubgraphSchema ~186 tokens
  Read one subgraph's published schema (SDL) from a variant, with its routing URL, revision, and last update time. This is the same read that `rover subgraph fetch` performs. Read one subgraph at a time: a whole supergraph document is much larger and can pass the token limit of the model. Provide the
• GetSupergraphSchema ~263 tokens
  Read the composed supergraph schema (SDL) for a graph variant, with the composition ID and any composition errors. This is the same read that `rover supergraph fetch` performs. A supergraph schema is the single schema that composition builds from every subgraph, and it carries federation directives
• GetTopOperations ~399 tokens
  Identify the most-used operations on a graph variant for a time range, with request counts, types, and signatures. Use to find high-traffic operations, detect unused operations, and prioritize findings by traffic impact. Provide graph ID, variant, and a from/to time range (ISO 8601 timestamps; `to`
• GetVariantDetails ~145 tokens
  Retrieve metadata for a graph variant: its identifier, federation version, the URL of its GraphQL endpoint, and its subgraph inventory (names only). Use this to assess a variant's composition setup, such as subgraph inventory and federation version compliance. Provide the graph ID and variant name (
• LintSchema ~254 tokens
  Lint a GraphQL schema document against the graph's lint rules and return each diagnostic's coordinate, severity level, message, rule, and source location, plus the error, warning, total, and ignored counts. This is the same check that `rover graph lint` and `rover subgraph lint` run. Nothing is publ
• PublishContract Sends messages · ~491 tokens
  Create or update a contract variant and start a launch for it, the same write that `rover contract publish` performs. A contract variant is a filtered view of another variant's schema, built by including and excluding schema elements by tag. The filter configuration replaces the previous one in full
• PublishGraphSchema Sends messages · ~260 tokens
  Publish a schema to a graph variant, the same write that `rover graph publish` performs. Use this for a monograph; use PublishSubgraph for one subgraph of a federated graph. Returns a result code, whether the publish succeeded, a human-readable message, and the hash of the published schema. This cha
• PublishPersistedQueries Sends messages · ~944 tokens
  Publish operations to a persisted query list, the same write that `rover persisted-queries publish` performs. A persisted query list is the set of operations a router accepts when it is configured to reject anything else. Operations you do not mention stay in the list unchanged: pass operations to a
• PublishProposalRevision Sends messages · ~998 tokens
  Save a new revision of a schema proposal by publishing changed subgraph schemas to its proposal variant, the same action as Save revision in GraphOS Studio. GraphOS composes the proposal variant, records the diff against the source variant, and runs schema checks on it. The source variant does not c
• PublishReadme Sends messages · ~188 tokens
  Replace the README of a graph variant, the same write that `rover readme publish` performs. The README is the Markdown document shown on the variant's page in GraphOS Studio. The new text replaces the whole README, so read the current one with GetReadme first if you intend to keep any of it. Provide
• PublishSubgraph Sends messages · ~308 tokens
  Publish a subgraph schema to a variant and start composition, the same write that `rover subgraph publish` performs. Returns whether the subgraph was created or updated, any composition errors, and the launch that started. This changes the schema registry and can change what the router serves. Run R
• RenameApiKey ~136 tokens
  Rename an API key in an organization, the same write that `rover api-key rename` performs. The key value and its access do not change. Returns the key's ID and new name. Provide the organization ID, the key ID, which GetApiKeys returns, and the new name.
• ReviewProposal ~266 tokens
  Approve or reject a revision of a schema proposal, with an optional comment, the same action as Review in GraphOS Studio. Only a requested reviewer can review, and calling this again replaces the caller's earlier review. Returns the proposal's status and its reviews, or an error with a message. Prov
• RunSchemaCheck ~247 tokens
  Start a schema check of a proposed schema against a variant, the same check that `rover graph check` starts. Use this for a monograph or for a whole supergraph schema; use RunSubgraphCheck for one subgraph. The check runs in the background, so this returns a workflow ID and a Studio URL, not a resul
• RunSubgraphCheck ~286 tokens
  Start a schema check of one proposed subgraph schema against a variant, the same check that `rover subgraph check` starts. The check runs in the background, so this returns a workflow ID and a Studio URL, not a result. Pass the returned workflowID to GetCheckResults to read the outcome. Provide the
• TagGraphArtifact ~166 tokens
  Assign a tag to a graph artifact, the same write that `rover graph-artifact tag` performs. If the tag does not exist, it is created. If it exists, it moves to this artifact, and any router that fetches by that tag receives the new artifact. Returns the artifact's ID and digest, or an error with a me
• UntagGraphArtifact ~169 tokens
  Delete a graph artifact tag from a graph, the same write that `rover graph-artifact untag` performs. The tag and its full history are removed, and any router that fetches by that tag can no longer resolve it. The artifact itself stays. Tags that Apollo manages, such as a variant's latest tag, cannot
• UpdateProposalStatus ~276 tokens
  Change the status of a schema proposal, the same action as the status menu in GraphOS Studio. DRAFT is for work in progress, OPEN asks reviewers to review, and CLOSED abandons the proposal. GraphOS accepts APPROVED only when the proposal has as many approvals as the graph requires, and it never acce
• ValidateOperations ~290 tokens
  Validate client GraphQL operations against a variant's published schema and return each problem's type (FAILURE, WARNING, INVALID), code, description, and the name of the operation it came from. This is the same check that `rover client check` runs. Nothing is published and no state changes. Provide

Browse

• GitHub tools
• Apollo tools
• Spreadsheets
• GitHub and code hosting

Related MCP servers

• Api Contract Validator
  Cloudflare Workers MCP server: api-contract-validator
• prxhub
  Search, cite, download, and publish .prx research bundles on prxhub.com.
• Apollo
  Apollo.io MCP — company and people data via api.apollo.io, the caller's OWN Apollo account (fleet…
• Hemrock MCP
  Hemrock financial modeling prompts: context primers, task prompts, checks, and best practices.
• CarShake
  Vehicle handover checklists, damage-documentation best practices, valet/rental/service FAQs.
• TestMu AI (formerly LambdaTest)
  Agentic AI quality engineering: run, debug and triage tests on real browsers and devices
• ALM X++ MCP Server
  D365 F&O: 90 AI tools over 200K+ objects, 25M+ cross-refs, 24M+ label translations.
• Avalanche AVAX MCP
  Search and retrieve Avalanche blockchain documentation for building on AVAX.

Badge for your README

[![AptLynx](https://aptlynx.net/badge/io.github.apollographql/graphos-mcp-server.svg)](https://aptlynx.net/servers/io.github.apollographql/graphos-mcp-server)

Listing text is written by the maker; AptLynx lists tools and does not vouch for them. Find another tool · Browse by topic · For agents