newman-ai-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| NEWMAN_MCP_ROOT | No | Allowed root for local file reads and writes. Defaults to the server's current working directory. | |
| POSTMAN_API_KEY | No | Postman API key used for Postman collection UIDs. | |
| NEWMAN_MCP_LLM_MODEL | No | Model name accepted by the OpenAI-compatible endpoint. | |
| NEWMAN_MCP_LLM_API_KEY | No | API key for the OpenAI-compatible provider. Keep it in the environment or a secret manager. | |
| NEWMAN_MCP_LLM_BASE_URL | No | API base URL for the OpenAI-compatible provider, for example https://api.openai.com/v1. | |
| NEWMAN_MCP_LLM_PROVIDER | No | AI provider to use. Defaults to local; set to openai-compatible to use an OpenAI-compatible endpoint. | local |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| inspect_postman_collectionA | Returns a lightweight map of the collection without running it, so the agent can see what exists before calling other tools. |
| validate_postman_collectionA | Instant static validation (no model or HTTP requests). Checks JSON, schema, script syntax, forbidden APIs, and undefined variables. |
| import_openapi_specA | Generates a Postman v2.1 collection from OpenAPI 3.0/3.1/Swagger 2.0 (JSON/YAML), or syncs an existing collection with a new spec version. Deterministic: uses openapi-to-postmanv2 without a model. |
| run_newman_collectionB | Runs a local or remote collection with full control over variables, timeouts, SSL, iterations, and state export. |
| generate_newman_reportA | Runs a collection and generates a report for auditing or CI/CD (JSON, JUnit, HTML Extra). |
| generate_cicd_pipelineA | Generates configuration to run Newman in CI/CD or Docker (GitHub Actions, GitLab CI, Azure DevOps, Jenkins, Dockerfile). |
| generate_tests_from_storyC | Generates API test cases from a user story or natural-language idea for a Postman collection (path, URL, or UID). |
| generate_test_datasetB | Generates a --iteration-data file (.json or .csv) with positive, negative, and boundary-value cases. |
| analyze_newman_failureB | Diagnoses a failure and suggests a corrected script or request. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 9 tools
Most tools target distinct lifecycle stages (inspect, validate, import, generate tests, run, report, CI/CD, dataset, diagnose). The main overlap is run_newman_collection vs generate_newman_report, which both execute a collection; the descriptions distinguish them (control vs. report artifact), but an agent could still hesitate. inspect vs validate is also close but clarified as map-only vs static checks.
All nine tools follow a consistent snake_case verb_noun pattern (run_*, generate_*, inspect_*, validate_*, import_*, analyze_*). Naming is predictable and self-describing across the whole surface.
Nine tools is well within the ideal 3-15 range for a Postman/Newman workflow server. Each tool covers a distinct phase (author, validate, import, run, report, CI/CD, diagnose) and none feels redundant.
The surface covers generation, inspection, validation, execution, reporting, CI/CD, test data, and failure diagnosis — a full lifecycle. Minor gaps: there is no tool to apply/persist the corrected script that analyze_newman_failure suggests, and no explicit collection-editing or environment-management operation.