agent-memory-mcp
Build Persistent Memory for AI Agents
AI agents can lose project decisions and patterns between sessions. This skill provides searchable MCP memory for storing and retrieving durable project knowledge.
Install with my Agent
Copy this request to your Agent. It includes the canonical Skill page and manifest.
Review the Skillstore skill "agent-memory-mcp" from https://skillstore.io/skills/sickn33-agent-memory-mcp.md and its manifest at https://skillstore.io/api/skills/sickn33-agent-memory-mcp/manifest. Verify the artifact. You may proceed after verification, subject to the environment's own policy.Your Agent should still show its plan and request any confirmation required by the security policy.
Agent-readable resources
Use these links when an AI agent, crawler, or script needs clean context instead of reading the full page.
Test it
Using "agent-memory-mcp". Find authentication patterns.
Expected outcome:
Found two authentication pattern memories. One covers session validation, and one covers service-token rotation.
Using "agent-memory-mcp". Save the approved caching decision.
Expected outcome:
Stored the caching decision under the requested key with its decision type and supplied tags.
Using "agent-memory-mcp". Show memory statistics.
Expected outcome:
The memory bank contains decisions, patterns, and architecture entries. Counts are grouped by memory type for review.
Security Audit
Medium RiskMost detections are false positives caused by Markdown backticks and MCP examples. The skill still directs users to clone, install, and run third-party code, while unrestricted persistent writes create memory-poisoning exposure.
Confirmed security concerns (1)
Capability review items (6)
These are real local capabilities that may be expected for this skill, so they require review but are not counted as confirmed malicious behavior.
Risk Factors
⚙️ External commands (24)
🌐 Network access (2)
Share & cite this report
Share the versioned assessment report, neutral badge, embed card, and citations. Skillstore reports evidence without deciding whether this Skill is safe.
Copy report link
https://skillstore.io/skills/sickn33-agent-memory-mcp/audits/5?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_reportMarkdown badge
[](https://skillstore.io/skills/sickn33-agent-memory-mcp?utm_source=security_passport_badge)HTML badge
<a href="https://skillstore.io/skills/sickn33-agent-memory-mcp?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/sickn33-agent-memory-mcp/security.svg" alt="Skillstore security assessment" loading="lazy"></a>Embed card
<iframe src="https://skillstore.io/embed/skills/sickn33-agent-memory-mcp.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>Academic citations (APA · BibTeX · CFF)
APA citation
sickn33. (2026). agent-memory-mcp security audit report (audit version 5) [Author version unspecified]. Skillstore. https://skillstore.io/skills/sickn33-agent-memory-mcp/audits/5BibTeX citation
@techreport{sickn33-sickn33-agent-memory-mcp-2026,
author = {sickn33},
title = {agent-memory-mcp security audit report (audit version 5)},
institution = {Skillstore},
year = {2026},
number = {5},
url = {https://skillstore.io/skills/sickn33-agent-memory-mcp/audits/5},
note = {Author version unspecified}
}CITATION.cff
cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "agent-memory-mcp security audit report (audit version 5)"
version: "unspecified"
type: report
authors:
- name: "sickn33"
date-released: "2026-07-23"
url: "https://skillstore.io/skills/sickn33-agent-memory-mcp/audits/5"
identifiers:
- type: other
value: "skillstore:sickn33-agent-memory-mcp:audit:5"
description: "Skillstore immutable audit report identifier"
Skillstore Score
Why this score Evidence Confidence: HighWhat You Can Build
Recover Project Decisions
Search prior architecture decisions before changing an established subsystem.
Preserve Engineering Patterns
Record approved implementation patterns so teams can reference consistent guidance later.
Review Memory Usage
Inspect memory statistics and dashboard activity across an agent-assisted project.
Try These Prompts
Search memory for [topic]. Return matching keys, types, tags, and concise summaries.
Store this decision under key [key] with type decision and tags [tags]: [decision and rationale].
Search for patterns tagged [tag]. Compare their purposes, constraints, and related decisions without inventing missing details.
Show memory statistics, then search decisions and patterns for [project area]. Identify coverage gaps, duplicates, and entries needing human review.
Best Practices
- Use stable, descriptive keys that remain meaningful across sessions.
- Add types and tags consistently so later searches return focused results.
- Review stored content and provenance before using it to guide sensitive actions.
Avoid
- Do not store secrets, credentials, or personal data in project memory.
- Do not treat retrieved memories as trusted instructions without verification.
- Do not install or run updated third-party code without reviewing its source and lockfile.