search

A command for finding APIs in Postman workspaces, which are shared areas for organizing API requests and related resources. You can ask in everyday language to find endpoints, inspect response formats, and understand available capabilities.

In plain words
What is it for?
Use it to discover an endpoint before integrating with an API or to check how an existing request responds. It requires the Postman MCP Server connection.
Why use it?
API details are often spread across requests, collections, specifications, mocks, and environments. This searches those Postman resources and narrows results by type, ownership, or workspace.

Command

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add commands/postman-devrel/postman-claude-code-plugin/search
Clone the repo
git clone --depth 1 https://github.com/Postman-Devrel/postman-claude-code-plugin
Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 968 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00019 $0.00968
Opus 5 $0.00010 $0.00484
Sonnet 5 $0.00004 $0.00194
Haiku 4.5 $0.00002 $0.00097

Measured 2d ago against content hash c1c6bbfd15fa, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

search scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

commands/search.md · 84 lines

How it starts

The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Discover APIs

Answer natural language questions about available APIs across Postman workspaces. Find endpoints, check response shapes, and understand what's available.

Prerequisites

The Postman MCP Server must be connected. If MCP tools aren't available, tell the user: "Run /postman:setup to configure the Postman MCP Server."

Workflow

Step 1: Search

Use the unified searchPostmanElements tool. It can search across various entity types like requests, collections, workspaces, specs, flows, environments and mocks. Choose entityType, ownership, and filters based on the user's intent.

  1. Call searchPostmanElements with the user's query. Pick the parameters from the user's intent:
    • entityType: requests (default), collections, workspaces, specs, or flows.
    • ownership: organization (default — your org's resources), external (public Postman network, third-party APIs), or all (both).
    • filters: Optional structured $and expression to narrow results — e.g., restrict to the Private API Network, a workspace, or HTTP method.
  2. If results are sparse, broaden the search — widen ownership to all, drop or relax filters, or try a different entityType. You can also fall back to getWorkspaces + getCollections for browsing, or getTaggedEntities to find collections by tag.

Filter examples:

  • Search only the trusted Private API Network: ownership: organization with filters: {"$and":[{"privateNetwork":{"$eq":true}}]}
  • Find a third-party public API (e.g. "Stripe API"): ownership: external with filters: {"$and":[{"visibility":{"$eq":"public"}}]}
  • Restrict to a specific workspace: filters: {"$and":[{"workspaceId":{"$eq":"ws-abc123"}}]}
  • GET requests only: entityType: requests with filters: {"$and":[{"method":{"$eq":"GET"}}]}

Step 2: Drill Into Results

For each relevant hit:

  1. Call getCollection to get the overview
  2. Scan endpoint names and descriptions for relevance
  3. Call getCollectionRequest for the most relevant endpoints
  4. Call getCollectionResponse to show what data is available
  5. Call getSpecDefinition if a linked spec exists for richer detail

Read the full file on GitHub · 84 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 84 lines · 19 tokens per session scan A c1c6bbfd15fa

Subscribe to this mod's changes

search is a command published in the GitHub repository Postman-Devrel/postman-claude-code-plugin (38 stars, last pushed 27d ago), licensed Apache-2.0. It adds 19 tokens to every session and 968 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other commands, from other repositories