# Echo Memory

> Shared memory for AI agents, as a graph in your own Postgres. Writes never call an LLM.

- name: io.github.ayushcodes10/echo-mem
- version: 0.5.3
- connection class: R1 (autonomous)
- trust: 93/100
- quality: –/100 (not scored)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/io.github.ayushcodes10%2Fecho-mem
- tools: https://api.protogrid.dev/v1/servers/io.github.ayushcodes10%2Fecho-mem/tools

**An agent can connect on its own if it already holds `ECHO_MEM_TOKEN`.** Remote endpoint behind a static API key or header. The registry never sees the value; the agent fills the placeholder.

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "echo-mem": {
      "type": "http",
      "url": "https://api.echo-mem.com/mcp",
      "headers": {
        "Authorization": "Bearer ${ECHO_MEM_TOKEN}"
      }
    }
  }
}
```

Placeholders to fill: `${ECHO_MEM_TOKEN}`.

## Trust

- hygiene: 100
- liveness: 100
- freshness: 100
- provenance: 75
- drivers: +repository +website +reachable +uptime-100% +updated-23d-ago
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality –/100 (not scored)

Not scored: fewer than three checks apply, usually because no remote answered a credential-free probe or the server is a local package.

### protocol: n/a (weight 25)

- n/a `protocol.modern`, `protocol.stateless`, `protocol.transport`, `protocol.list_ttl`: no remote answered a protocol handshake (not probed yet, unreachable, or local-only)

### 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: n/a (weight 30)

- n/a `tools.descriptions`, `tools.description_length`, `tools.schemas`, `tools.annotations`, `tools.directory_hints`, `tools.token_cost`, `tools.api_dump`: tool list unknown (behind auth, not probed, or empty)

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

- n/a `stability.changes`, `stability.rug_pull`: tool list unknown

### dependencies: 67 (weight 15)

- fail `deps.known_vulns`: 4 advisories to act on (malicious, or rated high or critical with a fix available): GHSA-jhr6-gm9c-rqjv in sentence-transformers@3.4.1 (direct, fixed in 5.6.0), GHSA-29pf-2h5f-8g72 in transformers@4.57.6 (indirect, fixed in 5.3.0), GHSA-fgcw-684q-jj6r in transformers@4.57.6 (indirect, fixed in 5.5.0), ...; 3 more of lower severity or without a fix
- pass `deps.mcp_sdk_version`: mcp 2.2.0, no known advisory
- pass `deps.resolvable`: echo-mem@0.5.3 resolved: 86 packages

- tools: unknown
- badge: [![protogrid quality](https://protogrid.dev/badge/io.github.ayushcodes10/echo-mem.svg)](https://protogrid.dev/servers/io.github.ayushcodes10/echo-mem)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

_No tool definition changes recorded._

## Dependencies

- pypi echo-mem@0.5.3: resolved, 85 dependencies, MCP SDK mcp 2.2.0
  - GHSA-jhr6-gm9c-rqjv (critical) in `` sentence-transformers@3.4.1 ``, direct, fixed in `` 5.6.0 ``, advisory summary: "sentence-transformers local model loading bypasses trust\_remote\_code and executes custom Python" https://osv.dev/vulnerability/GHSA-jhr6-gm9c-rqjv
  - GHSA-29pf-2h5f-8g72 (high) in `` transformers@4.57.6 ``, indirect, fixed in `` 5.3.0 ``, advisory summary: "HuggingFace transformers vulnerable to remote code execution" https://osv.dev/vulnerability/GHSA-29pf-2h5f-8g72
  - GHSA-fgcw-684q-jj6r (high) in `` transformers@4.57.6 ``, indirect, fixed in `` 5.5.0 ``, advisory summary: "huggingface/transformers: Arbitrary Code Execution During Model Initialization in the LightGlue Model Loading Path" https://osv.dev/vulnerability/GHSA-fgcw-684q-jj6r
  - GHSA-xrqw-3rrv-vx5w (high) in `` transformers@4.57.6 ``, indirect, fixed in `` 5.10.0 ``, advisory summary: "Transformers save\_pretrained path traversal allows arbitrary file writes through chat template names" https://osv.dev/vulnerability/GHSA-xrqw-3rrv-vx5w
  - GHSA-x9r9-c232-4q39 (high) in `` transformers@4.57.6 ``, indirect, no fix yet, advisory summary: "Hugging Face Transformers downloads custom generation code before trust consent" https://osv.dev/vulnerability/GHSA-x9r9-c232-4q39
  - GHSA-69w3-r845-3855 (moderate) in `` transformers@4.57.6 ``, indirect, fixed in `` 5.0.0rc3 ``, advisory summary: "HuggingFace Transformers allows for arbitrary code execution in the \`Trainer\` class" https://osv.dev/vulnerability/GHSA-69w3-r845-3855
  - PYSEC-2025-217 (unrated) in `` transformers@4.57.6 ``, indirect, no fix yet, advisory summary: "Hugging Face Transformers X-CLIP Checkpoint Conversion Deserialization of Untrusted Data Remote Code Execution Vulnerability. This vulnerability allows remote attackers to execute arbitrary code on affected installations of Hugging Face Transformers. User interaction is required to exploit this vuln" https://osv.dev/vulnerability/PYSEC-2025-217

Dependency graphs from deps.dev; advisories from OSV.dev, including the GitHub Advisory Database and the PyPI Advisory Database; all CC BY 4.0.

## Remotes

- https://api.echo-mem.com/mcp (streamable-http, auth api_key ${ECHO_MEM_TOKEN}, reachable true, uptime30d 1)

## Packages

- pypi echo-mem@0.5.3 secrets: ECHO_MEMORY_DATABASE_URL

## Tools (0)

_none observed_