# Agent Preflight

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

- name: com.agent-preflight/agent-preflight
- version: 0.2.0
- connection class: R0 (autonomous)
- trust: 79/100 flags: no-repository
- quality: 96/100 (strong)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/com.agent-preflight%2Fagent-preflight
- tools: https://api.protogrid.dev/v1/servers/com.agent-preflight%2Fagent-preflight/tools

**An agent can connect right now, no human step.** Remote endpoint, no authentication, reachable on the last probe.

## Connection (mcpServers)

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


## Trust

- hygiene: 80
- liveness: 99
- freshness: 85
- provenance: 55
- drivers: +dns-namespace +website +reachable +uptime-97% ~updated-30d-ago -no-repository
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 96/100 (strong)

### protocol: 88 (weight 25)

- pass `protocol.modern`: supports 2026-07-28 (server/discover)
- pass `protocol.stateless`: answers without a session
- pass `protocol.transport`: streamable HTTP
- warn `protocol.list_ttl`: tools/list declares ttlMs 0, so clients re-fetch it on every use

### authorization: n/a (weight 15)

- n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: 100 (weight 30)

- pass `tools.descriptions`: every tool has a description
- pass `tools.description_length`: descriptions are concise
- pass `tools.schemas`: every tool has an object input schema
- pass `tools.annotations`: 2 of 2 tools declare readOnlyHint or destructiveHint
- pass `tools.directory_hints`: every tool declares readOnlyHint, destructiveHint, idempotentHint and openWorldHint
- pass `tools.token_cost`: about 1,104 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: 100 (weight 15)

- pass `stability.changes`: 2 tool changes in 30 days
- pass `stability.rug_pull`: no tool changed its meaning under the same name

### dependencies: n/a (weight 15)

- n/a `deps.known_vulns`, `deps.mcp_sdk_version`, `deps.resolvable`: no npm or PyPI package

- tools: 2, about 1,104 tokens to load them all
- tool set hash: 98afc1391985be37a73f437a1b25ee48
- tools last changed: 2026-10-04T16:42:02.199Z
- badge: [![protogrid quality](https://protogrid.dev/badge/com.agent-preflight/agent-preflight.svg)](https://protogrid.dev/servers/com.agent-preflight/agent-preflight)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

- 2026-10-04 `preflight_tool_call` changed (description)
  - before: 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 $0.001 per settled POST interface. Full contract: https://agent-preflight.com/docs
  - after: 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
- 2026-10-04 `check_request` changed (description, inputSchema)
  - before: 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 $0.001 check.
  - after: 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.

Full history: https://api.protogrid.dev/v1/servers/com.agent-preflight%2Fagent-preflight/changes

## Remotes

- https://api.agent-preflight.com/mcp (streamable-http, auth none, reachable true, uptime30d 0.9741379)

## Packages

_none_

## Tools (2)

- `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.
- `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