MCP For Claude Marketplace
OpenAPI Context Window Packer

OpenAPI Context Window Packer MCP Connector for Claude

A+

Prune massive OpenAPI specs to fit within LLM context windows.

3 tools Official Updated Oct 1, 2026 Official Vinkius Partner
More Details Connect to Claude

The OpenAPI Context Window Packer is a precision engine designed to compress large OpenAPI/Swagger specifications. It solves the problem of AI agents failing to use tools because the API spec exceeds their token limit. By using compress_openapi_spec, you can prune paths not in your target list and strip unused components via dependency tracing. You can also use analyze_endpoint_coverage to verify presence and trace_schema_dependencies to identify required schemas.

openapiswaggercompressioncontext-windowtoken-optimization

3 tools expose this connector's capabilities to your AI agent.

analyze_endpoint_coverage

Analyzes endpoint coverage

compress_openapi_spec

Compresses OpenAPI spec

trace_schema_dependencies

Traces schema dependencies

See how to talk to your AI agent using OpenAPI Context Window Packer.

Check if my target endpoints are present in this spec.

The `analyze_endpoint_coverage` tool reports that 3 out of 5 target endpoints were found in the provided specification.

Compress this large OpenAPI spec to fit a 2000 token budget.

The specification has been compressed. The original size was estimated at 15,000 tokens, and the packed version is now approximately 1,850 tokens.

Which schemas are needed for the /users endpoint?

The `trace_schema_dependencies` tool identified that the `/users` endpoint requires the `User`, `Address`, and `Role` schemas.

The engine uses deterministic pruning. It removes all paths not in your `targetEndpoints` and then traces `$ref` pointers to remove any schemas that are no longer reachable, ensuring the resulting spec is structurally valid.

Related Connectors

Socket.dev (Dependency Security)

Socket.dev (Dependency Security) MCP

10 tools Official

Protect your software supply chain by scanning dependencies, checking package security scores, and monitoring threat feeds directly from your AI agent.

A+ View details →
Claude Verbosity Optimizer

Claude Verbosity Optimizer MCP

3 tools Official

A deterministic engine to detect and compress verbose LLM outputs to preserve context window budget.

A+ View details →
Observability & Tracing Calculator

Observability & Tracing Calculator MCP

3 tools Official

Deterministic engine for distributed tracing metrics, cost estimation, and anomaly detection.

A+ View details →
Beeceptor

Beeceptor MCP

29 tools Official

Mock APIs, intercept requests, and manage proxy rules directly from your AI agent.

A+ View details →