$ loading_
Query a bi-temporal property graph via MCP with auditable temporal reasoning.
Copy the install command and let the AI configure it · recommended for beginners
No copy-paste install info for "TGMS MCP Server" yet — see the docs or source repo.
Using the TGMS MCP Server, query which relationships between entity A and entity B were valid on 2024-03-01. Use verified temporal operators and return auditable supporting claims.
Returns the relationships valid at that time, along with auditable evidence or claim details.
Use the TGMS MCP Server to perform correction-aware time travel for entity C. Compare the timeline view before and after corrections, and mark which conclusions changed.
Outputs a diff showing how corrections changed the timeline and which facts or conclusions differ.
Based on the bi-temporal property graph in the TGMS MCP Server, answer whether entity D was associated with event E during a given period, and include auditable claims and temporal evidence.
Returns a time-grounded conclusion that can be checked and audited.
Researchers or data analysts can use it when they need to verify whether a fact held at a specific time or during a time range, using MCP-based queries against a bi-temporal property graph with supporting evidence.
When data has been corrected, developers can use it for correction-aware time travel to see how historical conclusions changed after the correction.
When LLM agents need traceable reasoning over graph data, this MCP tool lets them use verified temporal operators and reduce ambiguity in time-based queries.
It enables LLM agents to query a bi-temporal property graph via MCP and use verified temporal operators to produce auditable claims. It also supports correction-aware time travel for corrected historical views.
The provided materials do not include installation steps, dependencies, or key requirements. See the source repository for exact prerequisites.
From the description, it emphasizes bi-temporal querying, verified temporal operators, auditable claims, and correction-aware time travel. These features make it more suitable for scenarios that require temporal semantics and traceability.
Gives agents time awareness by tracking elapsed turns and day rollover.
Query breaking news, verified stats, and editorial analysis through MCP.
Extract, verify, cache, and search factual claims from text.
Enable AI agents to ingest, manage, and semantically search temporal knowledge graphs.
Query Google Calendar events by chat and evaluate MCP versus RAG capabilities.
Read Telegram subscriptions for natural-language search and digest creation.