Integration
REST, MCP, and AgentSkills examples for AgentPrizm governed AI agent memory.
Install
$ agentstack add mcp-agentprizm-integration ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ● Network access Used
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Links to your public security report.[](https://agentstack.voostack.com/security/report/mcp-agentprizm-integration) Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
AgentPrizm
AI agents forget. AgentPrizm remembers.
AgentPrizm is the governed memory and reusable skills layer for AI agents. It helps agents recall durable facts, lessons, directives, preferences, contacts, and bookmarks across sessions with scoped containers, validity windows, confidence signals, and recall receipts.
What AgentPrizm gives AI agents
- Persistent memory for agents that need context across sessions
- Scoped containers for users, teams, customers, environments, and agents
- Recall receipts so teams can see why an agent remembered something
- Fact-validity windows for time-sensitive information
- REST API and remote MCP integration
- Reusable AgentSkills for repeatable agent workflows
- Right-to-forget and safer memory hygiene patterns
Start here
- Website: https://agentprizm.com
- Docs: https://agentprizm.com/docs
- API reference: https://agentprizm.com/api-reference
- Security: https://agentprizm.com/security
- Integration examples: https://github.com/AgentPrizm/integration
Integration examples
The public integration repository includes:
- REST examples with curl
- JavaScript examples using Node 18+ native fetch
- Python examples using the standard library
- Remote MCP configs for Claude Code, Cursor, and Claude Desktop
- Example AgentSkills for support, sales, and PR review workflows
- Migration notes for DIY memory, Mem0, Zep, Letta, and pgvector-style stores
Example use cases
Coding agents
Recall repo conventions, architecture decisions, PR feedback, and repeated review lessons before writing code or reviewing pull requests.
Support agents
Recall customer preferences, plan facts, escalation rules, active tickets, and stale policy warnings before drafting replies.
Sales agents
Recall champion notes, blockers, procurement windows, renewal owners, objections, and next steps before outreach or call prep.
AI agencies and integrators
Partition memory by client, environment, and agent while shipping governed recall without maintaining a custom memory stack for every project.
Core line
Every recall should have a receipt.
Source & license
This open-source MCP server is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: AgentPrizm
- Source: AgentPrizm/integration
- License: MIT
- Homepage: https://agentprizm.com
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.