Konstruct MCP
Knowledge graph for AI agents. Query concepts, walk edges, get advisories.
Query, storage and vector-search services. Where a service is a server you host yourself, the listing says so rather than implying a hosted endpoint.
Knowledge graph for AI agents. Query concepts, walk edges, get advisories.
High-dimensional vector embedding semantic SimHash deduplication sentinel with LRU cache simulation
Your health data (weight, macros, weigh-ins) as MCP tools — in your own Supabase, zero custody.
Read-only, guarded SQL access for AI agents: PostgreSQL, MySQL, ClickHouse, Oracle, SQL Server, Db2
Read-only MCP server for 1C:Enterprise via OData with metadata and query builder tools.
Secretless database and cloud access via Akeyless RTA. Credentials never enter the model.
Find and fix drift between Supabase environments: schema, RLS, roles, auth, storage and more.
SQL validation, formatting, parsing, metadata extraction, linting, and security analysis.
Task queue, decisions and memory for coding agents. Local SQLite, no network. Requires Bun.
Let AI agents query data and act across all your business apps via MCP.
Control and query Rigol DHO824 oscilloscope for waveform capture and measurements
Query Spark SQL clusters via Thrift/HiveServer2. Works with Spark, EMR, Hive, Impala.
Read, write, and combine connected apps and databases with shared code and per-person permissions.
Safe, read-only database access for AI agents. 5 databases, batch queries, SQLGlot.
Policy-driven, read-only MCP server for safe database access from AI tools.
Personal finance ledger for AI agents — query spending, track bills, forecast cash flow.
SQLite-backed hybrid (vector + FTS) code search index for Claude Code over MCP.
Query OpenTelemetry traces from agent runs through MCP.
Read-first Redis MCP: SCAN key explorer, keyspace/TTL/memory/slowlog stats, DBA advisor
PostgreSQL MCP server - query, schema introspection, explain, and health checks for AI assistants
Enterprise PostgreSQL MCP secured by Aegis Zero-Trust to block unauthorized SQL injections.
Embedded, local-first agent memory: one SQLite file per namespace, no server, no cloud.
Local-first, lightweight issue tracker. Single binary, SQLite-backed, MCP-native.
Query trust scores for MCP servers and agent skills. Check if a tool is safe.