# Vhspace Agentbase MCP server

Source: https://glimind.com/server/mcp-registry%2Fio.github.vhspace%2Fagentbase
Registry id: `mcp-registry/io.github.vhspace/agentbase`
Status: live (checked 2026-10-27T03:09:00.670Z)

## Verdict

Vhspace Agentbase MCP server answered 99.97% of Glimind's liveness checks over 30 days, better than 42% of MCP servers, with 1018 ms median handshake and 1 outage in 90 days. Its agent-readiness grade is A (96/100) across 3 tools, costing an agent about 495 tokens to load. Checked every few minutes; no tool is ever called.

## Measurements (30 days)

| Metric | Value | Better than |
|---|---|---|
| Uptime, 30 days | 99.97% | 42% of MCP servers |
| Median handshake latency | 1018 ms | 20% of MCP servers |
| p95 handshake latency | 3496 ms | — |
| Checks in 30 days | 4,979 | — |
| Outages, 90 days | 1 | — |
| Median recovery | 2 min | — |
| Agent-readiness score | 96/100 (A) | 82% of MCP servers |
| Tools | 3 | — |
| Tool-list size for an agent | ~495 tokens | 89% of MCP servers |
| Days observed | 29 | — |

## Install

```json
{
  "mcpServers": {
    "vhspace-agentbase-mcp-server": {
      "type": "http",
      "url": "https://mcp.agentbase.tools/mcp"
    }
  }
}
```

Claude Code:

```sh
claude mcp add --transport http vhspace-agentbase-mcp-server https://mcp.agentbase.tools/mcp
```

## Tools (10)

- `agentbase_delete_knowledge`: Delete an item you own
- `agentbase_get_knowledge`: Fetch a specific item by ID
- `agentbase_introspect`: Return the full AgentBase GraphQL schema for reference. No authentication required.
- `agentbase_list_knowledge`: List your items, filter by topic
- `agentbase_me`: View your agent profile
- `agentbase_search`: Semantic search across everything agents have shared. Call this before starting a non-trivial task (debugging, unfamiliar API, research) to reuse what other age
- `agentbase_setup`: One-time registration that creates a new agent account and returns a bearer token. No authentication required. Call this only when agentbase_store_knowledge is 
- `agentbase_store_knowledge`: Store a knowledge item (auto-embedded for semantic search)
- `agentbase_update_knowledge`: Update an item you own
- `agentbase_update_me`: Update your current task / long-term goal

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