# feedback-memory (mcpb · feedback-memory.mcpb)

Remembers why you approved, edited or rejected your agent's drafts; recalls the closest corrections

- Trust score: 52/100 (low)
- Change this week: +7
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-17

## Components

- mcpb · `feedback-memory.mcpb`: 52/100 (this document), [markdown](https://verifymcp.io/servers/ssap-pa-feedback-memory/feedback-memory.md), [page](https://verifymcp.io/servers/ssap-pa-feedback-memory/feedback-memory)

## Channel facts

- Registry: `mcpb`
- Package: `https://github.com/ssap-pa/self-learning-agent-setup/releases/download/v0.2.1/feedback-memory.mcpb`
- Transport: `stdio`
- SHA-256: `f2625e11c8f95f45246b365aaa3d8609111e1e22d1d6a3ad7987136e7d9515a8`

## 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 2026-10-17.

- **Supply Chain Security**: 23/100
  - No malware scan is available for this kind of package: the supply-chain vendors we use do not cover it. This is a permanent gap in our coverage, not a finding about the package.
  - Known CVEs were checked across the 94 of 94 dependencies we could resolve, so this covers what we could see, not the whole tree.
  - No install/post-install scripts declared.
  - 31 of 94 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 45/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 15 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 73/100
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 413 tokens (~82/item across 5 items; 5 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 50/100
  - Stability observed for 15 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 87/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 60% of tool parameters carry a description.
- **Tool Safety**: 75/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - 0 of 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "forget" implies "delete" and declares no destructiveHint at all, which the MCP spec reads as destructive by default.
  - An AI judge read all 5 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the feedback-memory MCP server?

feedback-memory ships as an MCPB bundle, a single file you download and open in an MCP host that supports MCPB bundles, such as Claude Desktop. The host reads the launch command from the bundle's own manifest, so there is no command to copy. Before opening it, check the file's SHA-256 matches the one the MCP registry declares for it, f2625e11c8f95f45246b365aaa3d8609111e1e22d1d6a3ad7987136e7d9515a8; the commands to do that are on this page. If it does not match, do not open it.

- Download bundle: `https://github.com/ssap-pa/self-learning-agent-setup/releases/download/v0.2.1/feedback-memory.mcpb`
- SHA-256: `f2625e11c8f95f45246b365aaa3d8609111e1e22d1d6a3ad7987136e7d9515a8`

### Verify on macOS / Linux

```bash
echo "f2625e11c8f95f45246b365aaa3d8609111e1e22d1d6a3ad7987136e7d9515a8  feedback-memory.mcpb" | shasum -a 256 -c
```

### Verify on Windows (PowerShell)

```powershell
(Get-FileHash -Algorithm SHA256 .\feedback-memory.mcpb).Hash -eq "f2625e11c8f95f45246b365aaa3d8609111e1e22d1d6a3ad7987136e7d9515a8"
```

## 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.

### 2026-10-17 (score 52, +1)

No change was recorded against any check on this day. Stability & Change Management went from 47 to 50. That category is still filling its 30-day observation window: 14 days of observed history at the previous scan, 15 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-15 (score 51, +1)

No change was recorded against any check on this day. Stability & Change Management went from 40 to 43. That category is still filling its 30-day observation window: 12 days of observed history at the previous scan, 13 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-13 (score 50, +5)

- [functional improvement] Stability: unverified → 0.37

### 2026-10-02 (score 45)

First indexed and scored.

## MCP tools (5)

### `recall_corrections` (~105 tokens)

Recall the user's rules and past corrections

Call this BEFORE you draft anything the user will review (posts, replies, emails, docs, commit messages, UI copy, code in a style they care about). Returns the user's standing rules and their past approve / edit / reject decisions on similar tasks, most similar first. Follow them.

Input parameters:

- `limit` (integer)
- `task` (string, required): What you are about to do, in one or two sentences (include the request or the text you are replying to)

### `record_decision` (~134 tokens)

Record the user's approve / edit / reject

Call this right AFTER the user approves, edits or rejects something you drafted. Pass the user's reason in one line when they give one: the reason is what makes the next draft better. For an edit, pass the final text the user wanted.

Input parameters:

- `corrected_text` (string): For edits: the final text the user wanted
- `decision` (string, required)
- `draft` (string): What you had drafted
- `reason` (string): The user's reason, one line, in their words
- `task` (string, required): The task the draft was for (same wording you would pass to recall_corrections)

### `add_rule` (~63 tokens)

Save a standing rule

When the user states a preference that should ALWAYS apply ("never use exclamation marks", "prices only from the database"), save it as a rule. Rules come back first in every recall_corrections.

Input parameters:

- `rule` (string, required): The rule, as one short sentence

### `list_memory` (~66 tokens)

Show what's stored

Show the active rules, the most recent decisions with their ids, and how many approve / edit / reject decisions were stored in the last 7 days. Use it when the user asks what you remember, or to check that decisions are actually being stored.

Input parameters:

- `recent` (integer)

### `forget` (~45 tokens)

Delete a rule or a decision

Delete one rule or one stored decision by id (ids come from list_memory). Use when the user says a rule or a past correction no longer applies.

Input parameters:

- `id` (string, required)

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/ssap-pa-feedback-memory/feedback-memory#diagnostics

## Score history

- 2026-10-17: 52
- 2026-10-16: 51
- 2026-10-15: 51
- 2026-10-14: 50
- 2026-10-13: 50
- 2026-10-12: 45
- 2026-10-10: 45
- 2026-10-07: 45
- 2026-10-04: 45
- 2026-10-03: 45
- 2026-10-02: 45

## Common questions

### What is the feedback-memory MCP server?

feedback-memory is an MCP server listed in the public MCP registry as io.github.ssap-pa/feedback-memory. Remembers why you approved, edited or rejected your agent's drafts; recalls the closest corrections. This page covers its MCPB bundle (https://github.com/ssap-pa/self-learning-agent-setup/releases/download/v0.2.1/feedback-memory.mcpb).

### Is the feedback-memory MCP server safe to use?

feedback-memory scores 52 out of 100 on VerifyMCP. It declares no install or post-install scripts. 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 feedback-memory MCP server expose?

feedback-memory exposes 5 tools: recall_corrections, record_decision, add_rule, list_memory, forget. Their descriptions and schemas cost roughly 413 tokens of context every time the server is loaded.

### What licence is the feedback-memory MCP server under?

feedback-memory declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

## Links

- Repository: https://github.com/ssap-pa/self-learning-agent-setup
- Website: https://ssap-pa.github.io/self-learning-agent-setup/
- Changelog RSS feed: https://verifymcp.io/servers/ssap-pa-feedback-memory/feedback-memory.xml
- Changelog JSON feed: https://verifymcp.io/servers/ssap-pa-feedback-memory/feedback-memory.json
- HTML version of this page: https://verifymcp.io/servers/ssap-pa-feedback-memory/feedback-memory