Skip to main content
Glama
Postbuild MCP

Postbuild MCP

Official

Search & Filter Curated Launch Directories and Communities

postbuild_directories
Read-onlyIdempotent

Search and filter a local catalog of 85 launch directories by category, status, and minimum Domain Rating to shortlist submission targets without network calls.

Instructions

Search and filter the local catalog of 85 launch targets (74 software/AI/SaaS directories and 11 launch communities) without network calls or side effects. Filters (category substring, status state, and min_da Domain Rating floor) combine with logical AND and are capped at limit records (unlicensed sessions return a 5-directory preview; a Launch Pass license pb_live_... unlocks all 85); repeated calls in the same session return stateful delta stubs unless bypass_cache: true forces full record hydration. Use this tool to explore and shortlist directories by authority or submission type; do not use it to generate pre-filled launch URLs and Show HN copy (postbuild_dispatch) or to verify directory confirmation emails (postbuild_inbox).

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "postbuild_directories"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlNoProject URL whose domain scopes the session's directory state (default: 'https://www.postbuild.dev').https://www.postbuild.dev
limitNoMaximum directory records to return, from 1 to 85 (default: 25; capped at 5 without a Launch Pass license).
min_daNoMinimum Domain Rating (DR) threshold from 0 to 100 (default: 0).
statusNoSubmission workflow status filter: 'ready_auto', 'queued', or 'dispatched'.
categoryNoCase-insensitive category substring filter (e.g. 'AI', 'SaaS', 'Developer', 'MCP', 'Community', 'B2B').
bypass_cacheNoWhen true, disables session delta compaction and returns full directory records (default: false).

Output Schema

NameRequiredDescriptionDefault
_mcpNoStateful session cache metadata (`watermark`, `mode`, `total`, `returned`).
recordsYesMatched directory records ordered by relevance and Domain Rating.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed13 schema fields changedv2.1.24
    • addedInput schema / additionalProperties
      Added value: +false
    • addedInput schema / properties / bypass_cache / default
      Added value: +false
    • changedInput schema / properties / bypass_cache / description
      Previous value: -"Force fresh upstream query and full projection"New value: +"When true, disables session delta compaction and returns full directory records (default: false)."
    • changedInput schema / properties / category / description
      Previous value: -"Optional category filter (e.g. AI, SaaS, Developer, Launch)"New value: +"Case-insensitive category substring filter (e.g. 'AI', 'SaaS', 'Developer', 'MCP', 'Community', 'B2B')."
    • addedInput schema / properties / limit / default
      Added value: +25
    • changedInput schema / properties / limit / description
      Previous value: -"Max records to return (default: 25)"New value: +"Maximum directory records to return, from 1 to 85 (default: 25; capped at 5 without a Launch Pass license)."
    • addedInput schema / properties / min_da / default
      Added value: +0
    • changedInput schema / properties / min_da / description
      Previous value: -"Minimum Domain Rating (0-100)"New value: +"Minimum Domain Rating (DR) threshold from 0 to 100 (default: 0)."
    • changedInput schema / properties / status / description
      Previous value: -"Optional status filter (ready_auto, queued, dispatched)"New value: +"Submission workflow status filter: 'ready_auto', 'queued', or 'dispatched'."
    • addedInput schema / properties / status / enum
      Added value: +[
      +  "ready_auto",
      +  "queued",
      +  "dispatched"
      +]
    • addedInput schema / properties / url / default
      Added value: +"https://www.postbuild.dev"
    • changedInput schema / properties / url / description
      Previous value: -"Target URL (default: https://www.postbuild.dev)"New value: +"Project URL whose domain scopes the session's directory state (default: 'https://www.postbuild.dev')."
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
      +  "properties": {
      +    "_mcp": {
      +      "description": "Stateful session cache metadata (`watermark`, `mode`, `total`, `returned`).",
      +      "properties": {
      +        "mode": {
      +          "description": "Payload mode ('full' or 'delta').",
      +          "type": "string"
      +        },
      +        "total": {
      +          "description": "Total matching records before compaction.",
      +          "type": "number"
      +        },
      +        "watermark": {
      +          "description": "Current entity state watermark (e.g. 'v1').",
      +          "type": "string"
      +        }
      +      },
      +      "type": "object"
      +    },
      +    "records": {
      +      "description": "Matched directory records ordered by relevance and Domain Rating.",
      +      "items": {
      +        "properties": {
      +          "authType": {
      +            "description": "Required verification method (e.g. 'OTP (@postbuild.dev)', 'Direct Form', 'OAuth').",
      +            "type": "string"
      +          },
      +          "category": {
      +            "description": "Primary directory category.",
      +            "type": "string"
      +          },
      +          "dr": {
      +            "description": "Domain Rating (0-100).",
      +            "type": "number"
      +          },
      +          "id": {
      +            "description": "Directory identifier (e.g. 'dir-1').",
      +            "type": "string"
      +          },
      +          "name": {
      +            "description": "Directory or community name.",
      +            "type": "string"
      +          },
      +          "prefilledUrl": {
      +            "description": "URL with pre-populated query parameters when supported.",
      +            "type": "string"
      +          },
      +          "status": {
      +            "description": "Current dispatch status ('ready_auto', 'queued', or 'dispatched').",
      +            "type": "string"
      +          },
      +          "url": {
      +            "description": "Submission or listing URL.",
      +            "type": "string"
      +          }
      +        },
      +        "type": "object"
      +      },
      +      "type": "array"
      +    }
      +  },
      +  "required": [
      +    "records"
      +  ],
      +  "type": "object"
      +}
  2. First observedv2.1.23

TDQS

A4.6/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint, idempotentHint and closed-world, but the description adds substantive context the annotations cannot: no network calls, a 5-record preview without a `pb_live_...` license, and stateful delta stubs on repeat calls unless `bypass_cache: true`. That is genuinely useful behavioral disclosure; it falls short of 5 only because it doesn't say what a 'delta stub' actually looks like.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Purpose is front-loaded in the first clause, and every sentence carries information (filters, licensing, caching, alternatives). It is a dense single paragraph and the nested parentheticals make it slower to scan than it needs to be, but no sentence is filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a six-parameter read-only search tool with a full output schema, everything an agent needs is present: filter combination logic, licensing gate, caching behavior, and sibling routing. Return-value shape is correctly left to the output schema.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so baseline is 3, but the description adds semantics the schema does not: the three filters combine with logical AND, and results are capped at `limit`. It also explains the interaction between license state and the effective `limit` ceiling, which is not derivable from the schema alone.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('search and filter the local catalog of 85 launch targets') and quantifies scope (74 directories + 11 communities). It explicitly names the two siblings it is not (postbuild_dispatch for URL/HN copy, postbuild_inbox for confirmation emails), so an agent can discriminate without opening schemas.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives an affirmative use case ('explore and shortlist directories by authority or submission type') plus explicit exclusions routed to named alternatives. The license/delta behavior also tells the agent what to expect on repeated calls, removing a common source of mis-selection.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.