"Exploring Memory Persistence in DeepSeek Technology" matching MCP servers:

Enables capturing a tamper-evident, hash-chained local record of every AI agent tool call — both the decision before a tool runs and its outcome — so you can review what the agent actually did in order, detect edits, deletions, or reordering at the exact index, and export a signed evidence pack any third party can verify with no installs.

Lets an assistant read recorded production AI agent runs — steps, model and tool calls with arguments, and outcomes — along with the findings of comparison runs that checked a prompt or model change against those recordings, and verify a signed evidence bundle offline with no account or network. It is strictly read-only: no tool starts a replay or comparison, so nothing can spend money or act without a person deciding.

Enables AI assistants to query and analyze AI agent sessions from observability providers like Shepherd (AIOBS) and Langfuse, allowing users to debug agent runs, compare sessions, track performance, and analyze LLM usage patterns.

Enables a local AI agent to investigate service incidents by querying read-only telemetry such as service health, metrics, logs, and traces, then produce verifiable assessments with evidence links and uncertainty.

Self-hosted Nightingale (n9e) includes a native Streamable HTTP MCP server at /mcp for querying alerts, rules, metrics, logs, hosts and dashboards with the caller's existing permissions. Users deploy the Nightingale server themselves; the implementation and deployment documentation are in the main repository, and the official website is https://n9e.io.

Enables agent-neutral MCP clients to inspect native T3 inventory and results, persist signed events, perform explicit bounded delegation, and retain durable auditable receipts.

Enables querying and exploring KairosDB time-series data through natural language, including range/absolute queries, aggregations, last values, metric and tag listing, and health checks.

MCP server that wraps Drain3 for streaming log template mining, read-only matching, parameter extraction, and model persistence, exposing tools and resources to train on logs and query learned templates.

Read-only MCP server for exploring and searching OpenSearch clusters, enabling log analysis, index exploration, and query execution.

Enables data observability operations with the Sifflet platform. Supports exploring assets, monitors, incidents, generating monitor-as-code YAML from descriptions, and performing impact analysis.

Enables MCP-compatible agents to interact with Grafana instances for searching, creating, and updating dashboards, exploring logs via Loki, querying datasources, managing alerts, incidents, and on-call shifts, and accessing observability data.

A Python utility for adding usage tracking, analytics, and audit trails to MCP servers using SQLite-backed persistence. It enables developers to monitor tool, prompt, and resource activity and expose these statistics directly to LLM clients.

Enables querying and managing Azure Log Analytics workspaces using KQL (Kusto Query Language). Supports executing queries, managing saved queries, and exploring workspace tables and schemas with Service Principal authentication.

8 standalone MCP servers for SMBs — Guardrails (prompt injection, PII, secrets detection), FinOps (AI cost tracking and budgets), Observability (agent tracing), Smart Router (17+ models, 9 providers), Trust Score (governance scoring 0-100), Memory (persistent agent memory), ThinkSecure (runtime security + SOC2/GDPR audit), and A2A Lite (agent-to-agent protocol). 37 tools total, TNC credits

Tells an agent what went wrong with its own Ollama calls, in sentences with the fix: lost prompt cache and where the prompt stopped matching, context overflow, a model running partly on CPU, tool schemas crowding the prompt. Also the last turn in numbers and which local models fit in video memory. Local, read-only, nothing leaves the machine.

Production-grade MCP Gateway in Go featuring dynamic OpenAPI tool registration, RBAC governance, in-flight PII/DLP redaction, and structured JSON audit logging.

Enables agents to interact with the Logflare API by writing JavaScript functions that run in a Vercel Sandbox, using three tools: search, execute_read, and execute_write.

Enables AI assistants to search, summarize, and inspect Kibana/OpenSearch Dashboards logs through the user's logged-in browser session, eliminating the need for API keys or service accounts.

MCP-native agent evaluation and observability server. Log traces, evaluate output quality with 12 built-in rules (PII detection, prompt injection, cost thresholds), and track agent costs. Real-time dashboard, OTel-compatible spans. Self-hosted, MIT licensed.

A lightweight npm MCP server for deep Redis diagnostics, offering tools for memory, slowlog, clients, keyspace, latency, and config analysis with AI-powered recommendations.

Laravel Telescope-style debugging for Hono apps whose dashboard endpoint is also an MCP server: read recent exceptions with the request that produced them, recent requests filtered by status or duration, one request in full, and the slowest queries. Five read-only tools, zero runtime dependencies.

MCP server for analyzing Perfetto traces with LLMs — query .pftrace files in PerfettoSQL via Claude Code or any MCP client

Shows what is consuming your agent context window before a session starts: always-loaded skill descriptions ranked by token cost, skills installed more than once under different names, CLAUDE.md/AGENTS.md sizes including what their @import lines pull in, and MCP servers configured across clients. Read-only: no child processes, no network.

Every agent action is recorded in a SHA-256 hash chain. Prove to clients that your agent did what it said it did. Record, query, verify, and export agent activity.

Zabbix MCP server and CLI in one Go binary. 15 task-shaped tools: current problems, host investigation, why an alert did or did not arrive, metrics, maintenance. Zabbix 6.4+.

An MCP server that gives coding agents programmatic access to Sumo Logic logs via the Search Job API, enabling issue triage in preview deployments and production without leaving the editor.

A locally-hosted MCP (Model Context Protocol) server that gives Claude real tools to debug Docker containers — fetch logs, inspect memory/CPU, and run diagnostic commands inside a container, all from a chat with Claude Desktop.

A drop-in Model Context Protocol (MCP) server that lets an AI agent query PostgreSQL — read-only, enforced at the database level, with real SQL validation, timeouts, cost limits, OAuth 2.1, and an audit trail.

Provides read-only access to host system metrics (CPU, memory, disk), Docker container health/logs, and sandboxed log file analysis via MCP tools, enabling AI agents to monitor enterprise infrastructure safely.

An MCP server for Dead Man's Snitch that enables AI assistants to manage monitoring snitches, including creating, updating, checking in, and pausing monitors for scheduled tasks and cron jobs.