0
grade F
2 days ago
glama
iranti
Persistent shared memory for AI coding agents. Stores facts as entity/key/value triples with hybrid semantic search, task checkpoints, and conflict resolution — shared across Claude Code, Codex CLI, and GitHub Copilot.
Install from
M8ven verifies MCPs across every public registry — install directly from whichever one you prefer.
// key findings
🚨
Code appears obfuscated
12 files are unreadable to a human reviewer. Cannot audit what they do.
🔐
You'll be asked for 8 credentials: ANTHROPIC_API_KEY, GEMINI_API_KEY, GROQ_API_KEY, IRANTI_API_KEY, IRANTI_BOOTSTRAP_TOKEN, MISTRAL_API_KEY, OPENAI_API_KEY, POSTGRES_PASSWORD
These are read from process.env at runtime. Make sure you trust where they’ll be sent.
// required environment variables
This server reads these from
process.env. You'll be asked to provide them before it can run.🔐 secret
ANTHROPIC_API_KEYconfig
ANTHROPIC_BASE_URLconfig
ANTHROPIC_MODELconfig
CODEX_CLI_PATHconfig
DATABASE_URL— PostgreSQL connection string (pgvector required)🔐 secret
GEMINI_API_KEYconfig
GEMINI_MODELconfig
GITHUB_REF_NAME🔐 secret
GROQ_API_KEYconfig
GROQ_MODELconfig
IRANTI_AGENT_IDconfig
IRANTI_ALLOW_INSECURE_STARTUP🔐 secret
IRANTI_API_KEY— This writes .env.iranti with IRANTI_URL, , and agent identity. Each agent in a multi-agent system gets its own --agent-id.config
IRANTI_API_KEY_PEPPERconfig
IRANTI_ARCHIVIST_DEBOUNCE_MSconfig
IRANTI_ARCHIVIST_INTERVAL_MSconfig
IRANTI_ARCHIVIST_WATCH— Watch escalation files and auto-run maintenance (true/false)config
IRANTI_AUTO_REMEMBERconfig
IRANTI_BOOTSTRAP🔐 secret
IRANTI_BOOTSTRAP_TOKENconfig
IRANTI_CLAUDE_AGENT_DESCRIPTIONconfig
IRANTI_CLAUDE_AGENT_IDconfig
IRANTI_CLAUDE_AGENT_NAMEconfig
IRANTI_CLAUDE_ENTITY_HINTSconfig
IRANTI_CLAUDE_MAX_FACTSconfig
IRANTI_CLAUDE_SESSION_TASKconfig
IRANTI_CLOUD_CALLBACK_URLconfig
IRANTI_CONCURRENCY_STRESS_WRITESconfig
IRANTI_CONFLICT_RESOLUTION_TIMEOUT_MSconfig
IRANTI_DEBUGconfig
IRANTI_DECAY_ENABLEDconfig
IRANTI_DOCKER_BINconfig
IRANTI_ENV_FILEconfig
IRANTI_ESCALATION_DIRconfig
IRANTI_FAKE_DOCKER_PORTSconfig
IRANTI_HOMEconfig
IRANTI_INSTANCE_DIRconfig
IRANTI_INSTANCE_ENVconfig
IRANTI_INSTANCE_ENV_FILEconfig
IRANTI_INSTANCE_NAMEconfig
IRANTI_INSTANCE_RUNTIME_FILEconfig
IRANTI_MAX_BODY_BYTESconfig
IRANTI_MCP_AGENT_DESCRIPTIONconfig
IRANTI_MCP_AGENT_MODELconfig
IRANTI_MCP_AGENT_NAMEconfig
IRANTI_MCP_DEFAULT_AGENTconfig
IRANTI_MCP_DEFAULT_SOURCEconfig
IRANTI_MCP_HOSTconfig
IRANTI_MEMORY_ENTITYconfig
IRANTI_PERSONAL_MEMORY_ENTITYconfig
IRANTI_PORT— API port (default: 3001)config
IRANTI_PROJECT_ENVconfig
IRANTI_RATE_LIMIT_BACKENDconfig
IRANTI_REQUEST_LOG_FILEconfig
IRANTI_TEST_TOOL_SHIMconfig
IRANTI_TEST_WHERE_EXEconfig
IRANTI_TRUST_PROXYconfig
IRANTI_TX_MAX_WAIT_MSconfig
IRANTI_TX_TIMEOUT_MSconfig
IRANTI_URL— This writes .env.iranti with , IRANTI_API_KEY, and agent identity. Each agent in a multi-agent system gets its own --agent-id.config
IRANTI_VERBOSEconfig
IRANTI_WORKSPACE_IDconfig
LLM_PROVIDER— openai \ claude \ gemini \ groq \ mistral \ ollama \ mockconfig
LLM_PROVIDER_FALLBACK🔐 secret
MISTRAL_API_KEYconfig
MISTRAL_MODELconfig
NO_COLORconfig
OLLAMA_BASE_URLconfig
OLLAMA_MODEL🔐 secret
OPENAI_API_KEYconfig
OPENAI_BASE_URLconfig
OPENAI_MODEL🔐 secret
POSTGRES_PASSWORDconfig
POSTGRES_USERconfig
ProgramDataconfig
RATE_LIMIT_MAX_REQUESTSconfig
RATE_LIMIT_WINDOW_MSconfig
RELEASE_TAG// full audit trail
The full breakdown of what we checked, the deductions that landed, the network hosts, the dependency advisories, and concrete fix guidance is available to verified publishers.
// improvement guidance — verified publishers only
We have 7 concrete improvements we can share with the publisher of this MCP. Each comes with specific guidance to raise the trust score.
// embed badge in your README
[](https://m8ven.ai/mcp/nfemmanuel-iranti-1xxzwj)commit: fb394a76eb0a193ae3d043e7045999aa77984e09
code hash: 3639f9daaeb0e66706153c4019fe83e2d44b46d96835412e59d4620afc9f1a2c
verified: 4/18/2026, 6:17:53 PM