ZizkaDB

Install

uvx zizkadb-mcp==0.1.12

1 secret configuration field is declared. Names and values are omitted here.

Built for

Any MCP client. Works as a standard MCP server, so it can be added to any MCP client, including Claude, Cursor and Codex. Based on the listing description and package type. This is not a certification from those products.

Transports: stdio.

Links

• Repository
• Project site
• pypi package zizkadb-mcp
• Registry record

Search Memory

Audit report

Audited by AddonAudit.

Sandbox handshake completed and the published checks passed.

Automated smoke test, not a security guarantee.

Version

0.1.12

Audited

2 Nov 2026

Package

pypi zizkadb-mcp

Advisories

0 critical, 0 high, 0 medium, 0 low

Time to ready

899 ms

Network

Disabled

• Pass Version. Pinned pypi zizkadb-mcp@0.1.12
• Pass Known vulnerabilities. No critical, high, or medium advisories were returned.
• Pass License. MIT
• Pass Install scripts. No preinstall, install, postinstall, or prepare script.
• Pass Credential patterns. No credential patterns in the published artifact.
• Pass Package size. 11.0 KB
• Pass Maintainer activity. Active 2 days ago.
• Pass Sandbox. MCP handshake completed. 13 tools listed. Tool count measured offline in our sandbox; some servers load more tools when connected.

Tools

• log_event Log an event to ZizkaDB. Use this every time your agent takes an action: a tool call, a decision, a user message, or an agent response. Logging builds the causal graph that powers why(), search_memory(), and get_context(). Args: agen
• reset_log_chain Start a fresh causal chain (new session_id, clear parent_id).
• search_memory Search over all logged agent events. Finds past decisions, tool calls, conversations, or any event. Works on any server: keyword search without embeddings, keyword + meaning (hybrid) with them. Useful before a new task to see what happene
• verify_chain Prove an agent's history is untouched. Rechecks every event's checksum and its link in the agent's hash chain. "intact": true means no event was edited, removed or reordered (GDPR deletions show up as tombstones, not breaks). Keep "chain_
• get_context Get a formatted memory context block ready to inject into a system prompt. This is the drop-in replacement for LLM-provided memory (Claude Projects, ChatGPT memory). It combines recent events with semantically relevant past events, fits w
• why Trace the causal chain that led to an event. Given any event ID, walks back through parent_id links to reconstruct the full decision tree: user message -> tool call -> result -> response. Essential for debugging why an agent did something
• query_events List recent events for an agent. Args: agent: Agent identifier to query limit: Number of events to return (default 20) event_type: Filter by event type, e.g. "tool_call" (optional) Returns: List of events ordere
• time_travel Replay the exact state of an agent at a specific point in time. Reconstructs what the agent knew and had done up to that moment. Useful for investigating complaints ("what did the agent tell them at 3pm?") or comparing behaviour across ve
• get_baseline Behavioral baseline and drift score for an agent.
• get_token_usage Token usage and cost report for an agent over a date range.
• get_token_optimization Deterministic token optimization suggestions from real usage events.
• memory_diff Summarise what happened in a session. Returns event counts, types seen, causal depth, whether any errors occurred, and event types that had never appeared in prior sessions. Call this at the end of a session to understand what changed. A
• forget Delete all events matching a filter (GDPR right to erasure). Removes events from both the database and the vector index. Commonly used to delete all data for a specific user on request. Args: filter_key: Field in event data to matc

[11/02/26 09:22:26] INFO     Processing request of type            server.py:733
                             ListToolsRequest                                   
                    INFO     Processing request of type            server.py:733
                             ListResourcesRequest                               
                    INFO     Processing request of type            server.py:733
                             ListPromptsRequest

Raw audit JSON

Metadata checks

• Repository activity: Active in the last 180 days
• License: Recognized SPDX id
• Metadata quality: High

Score 100 uses public metadata only. It is separate from the audit tier. Payment never changes a score. How listings are checked.