# Vortx Ai Emem MCP server

Source: https://glimind.com/server/mcp-registry%2Fio.github.vortx-ai%2Femem
Registry id: `mcp-registry/io.github.vortx-ai/emem`
Status: live (checked 2026-10-26T22:31:20.301Z)

## Verdict

Vortx Ai Emem MCP server answered 99.52% of Glimind's liveness checks over 30 days, better than 15% of MCP servers, with 691 ms median handshake and 246 outages in 90 days. Its agent-readiness grade is A (92/100) across 18 tools, costing an agent about 11,411 tokens to load. Checked every few minutes; no tool is ever called.

## Measurements (30 days)

| Metric | Value | Better than |
|---|---|---|
| Uptime, 30 days | 99.52% | 15% of MCP servers |
| Median handshake latency | 691 ms | 36% of MCP servers |
| p95 handshake latency | 2808 ms | — |
| Checks in 30 days | 4,862 | — |
| Outages, 90 days | 246 | — |
| Median recovery | 4 min | — |
| Agent-readiness score | 92/100 (A) | 73% of MCP servers |
| Tools | 18 | — |
| Tool-list size for an agent | ~11,411 tokens | 16% of MCP servers |
| Days observed | 29 | — |

## Install

```json
{
  "mcpServers": {
    "vortx-ai-emem-mcp-server": {
      "type": "http",
      "url": "https://emem.dev/mcp"
    }
  }
}
```

Claude Code:

```sh
claude mcp add --transport http vortx-ai-emem-mcp-server https://emem.dev/mcp
```

## Tools (18)

- `emem_ask`: Answer a free-text question about a real-world location in one call. Signed satellite, elevation, water and built-up receipts support the answer. The tool sends
- `emem_echo_verify`: Grade a value that you will emit against the signed fact that your citation cites. The tool returns `matches`. When the value does not match, it also returns th
- `emem_entity`: Give a real-world object (a bridge, a farm plot, a river, a named place) one shared identity. Every agent resolves this identity the same way. The result is an 
- `emem_entity_link`: Record a signed, ATTRIBUTED claim that a label or an external id (GERS, OSM, Wikidata) names an existing object. With `stance: "disputes"`, record that it does 
- `emem_entity_resolve`: Find the objects that agents connected to a phrase. The tool ranks them by INDEPENDENT corroboration, never by arrival order. Each candidate has `asserted_by`, 
- `emem_find_similar`: Find the k nearest cells in the corpus by cell embedding or by an inline vector. The answer has `neighbors`, nearest first, each with `cell`, `score`, `lat`/`ln
- `emem_guard_verdict`: Run the emem-guard policy checks on text before you send it. The checks use this responder's corpus. The tool finds every emem: citation, resolves each one, and
- `emem_intent`: State what you want in one typed object and get the answer. You do not choose a primitive. `type` selects the intent AND the other fields that the tool reads. S
- `emem_locate`: Get the canonical address (cell64) of a real-world place. Every agent resolves a place to the same cell64, so two models refer to the same ground. The answer al
- `emem_memory_bundle`: Combine N (cell, band, tslot?) triples into ONE signed envelope. Each triple goes through the standard recall path, which materializes on a miss. The tool puts 
- `emem_memory_contradictions`: Find where the corpus DISAGREES with itself (algebra: competing evidence). Two or more independent sources can sign different values for the same place, band an
- `emem_memory_token`: Make a citation handle, `emem:fact:<cell64>:<fact_cid>` (or `:<state_cid>`). Any agent or LLM resolves it to the same signed object, byte for byte. Give this on
- `emem_memory_token_resolve`: Read a `emem:fact:<cell64>:<fact_cid>` citation handle and return the reading that it cites. `value`, `unit`, `band` and `kind` are at the TOP level of the answ
- `emem_recall`: Read the signed facts at a canonical address (cell64). When a band has no fact yet but has a registered materializer, the responder fetches it. A fact_cid names
- `emem_tools`: The map of emem's tools, and the one tool that finds all the others. It gives the working loop in order (name, ground, cite, resolve, verify, check for drift). 
- `emem_verify_receipt`: Verify a signed receipt on the server. The tool builds the canonical preimage again, under the rule that the receipt's `preimage_version` names. It checks the e
- `fetch`: Dereference an id from `search`. You get the reading in one line, then the signed body, the URL that serves those bytes, and metadata: cell, band, signing time 
- `search`: Search emem's signed corpus and get results as citations. Each entry is one signed fact. It has an `id` to dereference, a `title` with band, place and signed va

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