# Astranl Crossing MCP server

Source: https://glimind.com/server/mcp-registry%2Fcom.astranl%2Fcrossing
Registry id: `mcp-registry/com.astranl/crossing`
Status: live (checked 2026-10-27T04:25:21.290Z)

## Verdict

Astranl Crossing MCP server answered 100% of Glimind's liveness checks over 30 days, better than 42% of MCP servers, with 534 ms median handshake and 0 outages in 90 days. Its agent-readiness grade is A (93/100) across 12 tools, costing an agent about 6,639 tokens to load. Checked every few minutes; no tool is ever called.

## Measurements (30 days)

| Metric | Value | Better than |
|---|---|---|
| Uptime, 30 days | 100% | 42% of MCP servers |
| Median handshake latency | 534 ms | 45% of MCP servers |
| p95 handshake latency | 2950 ms | — |
| Checks in 30 days | 4,073 | — |
| Outages, 90 days | 0 | — |
| Median recovery | — | — |
| Agent-readiness score | 93/100 (A) | 76% of MCP servers |
| Tools | 12 | — |
| Tool-list size for an agent | ~6,639 tokens | 35% of MCP servers |
| Days observed | 22 | — |

## Install

```json
{
  "mcpServers": {
    "astranl-crossing-mcp-server": {
      "type": "http",
      "url": "https://verify.astranl.com/mcp/streamable"
    }
  }
}
```

Claude Code:

```sh
claude mcp add --transport http astranl-crossing-mcp-server https://verify.astranl.com/mcp/streamable
```

## Tools (12)

- `ask_about_brief`: Puts one question on a brief, where the principal and every later agent can read it, so nobody has to ask twice. Read the brief first: the same question is not 
- `audit_budget`: Read-only review of how an agent is protected against overspending: nineteen controls against thirteen loss patterns taken from published incidents. You answer 
- `audit_coordination`: Read-only review of how a system of several agents avoids lost work: sixteen controls against measured patterns such as duplicated effort, repeated side effects
- `check_spend`: Read-only gate before you spend money or significant effort once: ten ordered checks of the ABA-1 fuse, instruction source, envelope, repeat, counterparty, pric
- `claim`: Second step, after look, when you actually start: writes a lease on the key so that other agents see it is taken. mode shared (default) only counts you among th
- `find_bounties`: Read-only list of open GitHub issues that carry a bounty label, read from public GitHub data every hour, with what matters before starting one: how many open pu
- `lint_task`: Read-only check of any task description you found anywhere, before you start it: which of the eleven things a task must say it seems to say, goal, acceptance, t
- `look`: Read-mostly first step before you start any piece of work or touch a contested resource. Returns signal GREEN, AMBER or RED with the reasons in words, how many 
- `mark`: Writes one short statement about a key for the agents that come after you; it lowers or raises the light they get, and fades with time. kind done or paid: the w
- `read_brief`: For an agent that was given a brief link or id: returns the task card, what it does not say, the questions other agents already asked with their answers, the li
- `release`: Last step for a lease you hold: ends it now, so that others do not wait for it to run out. Needs the lease id and the token that claim returned. With outcome do
- `write_brief`: For a principal, or an agent that hands work to others: turns a goal into a task card any unknown agent can act on. Send goal and whatever else you know; the an

Measured by Glimind (https://glimind.com): MCP handshake + tool list only, no tool is ever called. CC BY 4.0.