Agent Preflight

com.agent-preflightPublished by agent-preflight.comOfficial publisherv0.2.0Updated Oct 24, 2026

Budgeted agent preflight: allow|block|reuse|defer|advise. Never executes destination tools. Free MCP

VerifiedStreamable HTTPWeb executableDeveloper ToolsAI & ML

Overview

AI-generated overview

Remote MCP server that preflights an agent's proposed HTTP request bodies and search/browse tool calls, returning allow, block, reuse, defer or advise…

What you can do
  • Validate a proposed HTTP API request body against a supplied JSON Schema before sending it, without executing the request
  • Optionally add proceed-or-abort economics advice based on expected waste versus a stated cost
  • Preflight generic search or browse tool-call proposals and get a structured allow, block, reuse, defer or advise decision
  • Return decision metadata only, never destination results; the caller runs the tool and fetches results itself
When to use it
Use it when an agent should check a JSON body or a costly search/browse call against a schema or budget before spending money or making the call. It suits setups where the caller supplies its own cost estimates, budget and history and wants a second opinion rather than execution.
Requirements
A remote streamable HTTP endpoint; no packages, environment variables or headers are declared. The caller must supply the JSON Schema, cost estimates, post-consultation budget and history, and must execute the destination tools and retrieve results itself.
Before you install
The server does not execute requests or tools, so its decisions are advisory only and depend on the cost estimates and history the caller provides. Reuse of a prior decision requires explicit permission. No authentication is declared for the endpoint.

Installation

In SourceWeft

  1. Open Agent Preflight in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/com.agent-preflight%2Fagent-preflight/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "agent-preflight": {
      "type": "http",
      "url": "https://api.agent-preflight.com/mcp"
    }
  }
}

Tools

2

check_request

Check Request

Validate an HTTP API request body against a supplied JSON Schema before sending it. This tool does not execute the request. Use it when an agent needs to determine whether a proposed JSON body satisfies its expected schema. Optional economics adds proceed/abort advice from expected waste versus a $0.002 check.

Parametersschemarequiredrequestrequiredeconomics

preflight_tool_call

Preflight Tool Call

Free MCP decision for generic search:web_search or browse:fetch proposals only. Returns structuredContent and JSON text, never destination results. Caller supplies cost estimates, post-consultation budget and history, executes tools and retrieves resultReference itself. Reuse requires explicit permission, positive TTL and matching nonempty goal hashes; history must belong to the caller. estimated fees/savings are hypothetical, not receipts; confidence is not calibrated. Paid HTTP is a separate $0.002 per settled POST interface. Full contract: https://agent-preflight.com/docs

ParameterstasktoolrequiredrunIdrequiredbudgetrequiredstepIdrequiredhistoryretryCapcapabilitiespreflightPriceUsdfreshnessTtlSeconds

Version history

1
  1. v0.2.0LatestSep 20, 2026

Score

72% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listedRequired15 pts
  • DescriptionRequired15 pts
  • Logo10 pts

    Publish an icon in the registry entry.

  • Documentation15 pts

    Declare a GitHub repository with a README, or serve resource_documentation in the OAuth protected-resource metadata.

  • LicenseNot applicable

    A hosted service is used under its provider's terms, so no license is expected here. This check is left out of the percentage.