This server bundles three backend services into 18 tools for agent infrastructure. The memory system gives you a namespaced key-value store with SQLite FTS5 search, batch operations, and TTL expiry. Drift detection lets you set up golden test cases against HTTP endpoints with cron scheduling and diff tracking to catch API changes before they break your workflows. Trust receipts generate HMAC-SHA256 signed records of agent actions for audit trails with online and offline verification. Each service requires its own API key. Reach for this when you're building agents that need persistent state, monitoring of external APIs, or cryptographically verifiable action logs.
MCP server with 18 tools for AI agent infrastructure — persistent memory, API drift detection, and HMAC-signed trust receipts.
npx @lulzasaur9192/agent-infra-mcp
{
"mcpServers": {
"agent-infra": {
"command": "npx",
"args": ["-y", "@lulzasaur9192/agent-infra-mcp"],
"env": {
"AGENT_MEMORY_API_KEY": "your-key",
"AGENT_DRIFT_API_KEY": "your-key",
"TRUST_RECEIPT_API_KEY": "your-key"
}
}
}
}
Persistent key-value store with namespaces, metadata, TTL, and FTS5 full-text search.
memory_store — Store a memory (namespace + key + value)memory_store_batch — Batch store up to 100 memoriesmemory_list — List memories in a namespacememory_get — Get a specific memorymemory_update — Update value, metadata, or TTLmemory_delete — Delete a memory or entire namespacememory_search — Full-text search with metadata filteringmemory_stats — Usage statisticsMonitor API endpoints for unexpected changes with golden test cases and cron scheduling.
drift_create_test — Register a golden test (exact/subset/contains/status match)drift_list_tests — List all testsdrift_run_test — Execute a test manuallydrift_test_history — View run history and diffsdrift_update_test — Update test configurationdrift_delete_test — Remove a testdrift_dashboard — Overview with drift rate and response timesHMAC-SHA256 signed, tamper-proof records of agent actions for audit trails.
receipt_issue — Issue a signed receipt for an agent actionreceipt_verify — Verify receipt integrity (online or offline)receipt_list — List receipts with filtersEach service uses its own API key:
| Service | Env Var | API |
|---|---|---|
| Memory | AGENT_MEMORY_API_KEY | agent-memory-api |
| Drift | AGENT_DRIFT_API_KEY | agent-drift-api |
| Receipts | TRUST_RECEIPT_API_KEY | trust-receipt-api |
MIT
AGENT_MEMORY_API_KEYAPI key for Agent Memory service
AGENT_DRIFT_API_KEYAPI key for Agent Drift Detection service
TRUST_RECEIPT_API_KEYAPI key for Trust Receipt service
io.github.ericm1018/skillfm-llm-cost-optimizer-openai-anthropic-usage
io.github.mikerawsonnz/llm-orchestration-agent
io.github.mikerawsonnz/authenticated-llm-agent
labforgedev/copilot-memory-mcp
csoai-org/agent-prompt-injection-firewall-mcp
io.github.mikerawsonnz/authenticated-multi-llm-agent