# io.github.theprodsde/agent-memory (pypi · agent-memory-sdk)

Persistent agent memory with a decision layer: replay, restore, verify, or none — explainable.

- Trust score: 54/100 (low)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-23

## Components

- pypi · `agent-memory-sdk`: 54/100 (this document), [markdown](https://verifymcp.io/servers/theprodsde-agent-memory/agent-memory-sdk.md), [page](https://verifymcp.io/servers/theprodsde-agent-memory/agent-memory-sdk)

## Channel facts

- Registry: `pypi`
- Package: `agent-memory-sdk`
- Version: `0.1.5`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-09-23.

- **Supply Chain Security**: 74/100
  - No malware found by supply-chain analysis.
  - A critical CVE affects chromadb, and no fixed version has been published yet.
  - Runs hatchling.build at install time, a recognised native-build step with no shell scripting around it.
  - 10 of 96 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 32/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - License check failed: no license is declared.
  - Actively maintained (last published 0 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 65/100
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 317 tokens (~45/item across 7 items; 7 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 0/100
  - Stability not yet verified: not enough scan history yet (needs a 30-day window).
- **Tool Coverage**: 71/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 0% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Tool Safety**: 75/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - 0 of 2 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "forget_memory" implies "delete" and declares no destructiveHint at all, which the MCP spec reads as destructive by default.
  - An AI judge read all 7 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).

**Unverified: 1 category.** A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.

## Install

### How do I install the io.github.theprodsde/agent-memory MCP server?

io.github.theprodsde/agent-memory runs locally as a PyPI package, launched with uvx agent-memory-sdk. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add theprodsde-agent-memory -- uvx agent-memory-sdk
```

### Cursor

```json
{
  "mcpServers": {
    "theprodsde-agent-memory": {
      "command": "uvx",
      "args": [
        "agent-memory-sdk"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "theprodsde-agent-memory": {
      "command": "uvx",
      "args": [
        "agent-memory-sdk"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add theprodsde-agent-memory -- uvx agent-memory-sdk
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "theprodsde-agent-memory": {
      "type": "local",
      "command": [
        "uvx",
        "agent-memory-sdk"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add theprodsde-agent-memory --command uvx --arg agent-memory-sdk
```

### Hermes

```yaml
mcp_servers:
  theprodsde-agent-memory:
    command: "uvx"
    args: ["agent-memory-sdk"]
```

### Netclaw

```json
{
  "McpServers": {
    "theprodsde-agent-memory": {
      "Transport": "stdio",
      "Command": "uvx",
      "Arguments": [
        "agent-memory-sdk"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add theprodsde-agent-memory -t stdio -c uvx -a agent-memory-sdk
```

### Other

```json
{
  "mcpServers": {
    "theprodsde-agent-memory": {
      "command": "uvx",
      "args": [
        "agent-memory-sdk"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-09-22 (score 54)

First indexed and scored.

## MCP tools (7)

### `remember_memory` (~103 tokens)

Store a query/response pair in persistent agent memory.

ttl accepts formats like "30d", "24h", "60m", "3600s".

Input parameters:

- `confidence` (number)
- `memory_type` (string)
- `metadata_json` (string)
- `query` (string, required)
- `requires_verification` (boolean)
- `response` (string, required)
- `scope` (string)
- `tags`
- `ttl`

Output parameters:

- `result` (string)

### `resolve_memory` (~76 tokens)

Retrieve memory and decide how the agent should respond.

Actions: replay, restore, verify, none
Modes: auto (default), replay, restore, verify

Input parameters:

- `enable_verify` (boolean)
- `mode` (string)
- `query` (string, required)
- `scope`
- `top_k` (integer)

Output parameters:

- `result` (string)

### `list_memories` (~47 tokens)

List stored memories with pagination and optional scope filter.

Input parameters:

- `include_archived` (boolean)
- `limit` (integer)
- `offset` (integer)
- `scope`

Output parameters:

- `result` (string)

### `get_memory_by_id` (~25 tokens)

Fetch a single memory by ID.

Input parameters:

- `memory_id` (string, required)

Output parameters:

- `result` (string)

### `forget_memory` (~22 tokens)

Delete a memory by ID.

Input parameters:

- `memory_id` (string, required)

Output parameters:

- `result` (string)

### `archive_memory` (~26 tokens)

Archive a memory so it is excluded from retrieval.

Input parameters:

- `memory_id` (string, required)

Output parameters:

- `result` (string)

### `consolidate_memories` (~18 tokens)

Merge near-duplicate memories into summary entries.

Output parameters:

- `result` (string)

## Diagnostics

Captured diagnostic sections: Provenance, Install scripts, Vulnerabilities, Dependencies. The full working is on the page: https://verifymcp.io/servers/theprodsde-agent-memory/agent-memory-sdk#diagnostics

## Score history

- 2026-09-23: 54
- 2026-09-22: 54

## Common questions

### What is the io.github.theprodsde/agent-memory MCP server?

io.github.theprodsde/agent-memory is an MCP server listed in the public MCP registry as io.github.theprodsde/agent-memory. Persistent agent memory with a decision layer: replay, restore, verify, or none, explainable. This page covers its PyPI package (agent-memory-sdk).

### Is the io.github.theprodsde/agent-memory MCP server safe to use?

io.github.theprodsde/agent-memory scores 54 out of 100 on VerifyMCP. We recorded 8 known advisories against it as of 23 September 2026. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the io.github.theprodsde/agent-memory MCP server expose?

io.github.theprodsde/agent-memory exposes 7 tools: remember_memory, resolve_memory, list_memories, get_memory_by_id, forget_memory, and 2 more. Their descriptions and schemas cost roughly 317 tokens of context every time the server is loaded.

### Is the io.github.theprodsde/agent-memory MCP server still maintained?

io.github.theprodsde/agent-memory is still listed as active in the MCP registry. We last reached this channel on 23 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- PyPI project: https://pypi.org/project/agent-memory-sdk/
- Socket report: https://socket.dev/pypi/package/agent-memory-sdk
- Repository: https://github.com/TheProdSDE/agent-memory-sdk
- Changelog RSS feed: https://verifymcp.io/servers/theprodsde-agent-memory/agent-memory-sdk.xml
- Changelog JSON feed: https://verifymcp.io/servers/theprodsde-agent-memory/agent-memory-sdk.json
- HTML version of this page: https://verifymcp.io/servers/theprodsde-agent-memory/agent-memory-sdk