"Finding Ohad Zafrir's LinkedIn Profile" matching MCP servers:

An MCP server that decodes V8 CPU profiles into token-efficient bottleneck summaries for AI agents, enabling them to analyze CPU consumption, call trees, GC pressure, and async bottlenecks.

Enables coding agents to read performance findings from sixty, get detailed evidence for each finding, and close or resolve them with descriptions, while also checking service telemetry and providing installation instructions.

Enables analyzing coding-agent session transcripts to measure tool efficiency, detect loops, track test outcomes, and report costs, with MCP tools for listing sessions, analyzing sessions, finding loops, and generating cost reports.

agent-bom is an open security scanner and self-hosted control plane for AI, MCP, and cloud infrastructure. The default scan profile in MCP server mode exposes 8 MCP tools. Additional profiles provide inventory, findings, compliance, graph, and runtime workflows. See the published Glama release for its packaged version.

Enables coding agents to profile and disassemble GPU kernels, benchmark and compare candidate rewrites against baselines, and run an autonomous speedrun loop that verifies and records results.

Enables AI assistants and MCP clients to analyze offline Oracle AWR/ASH reports in HTML or text across Oracle 10g–23ai, including single-instance and RAC global reports, returning report type, version, active sessions, load profile, top waits and SQL with version-aware tuning advice plus a prioritized top-3 summary, all locally without an Oracle client or database connection.

Enables Claude Desktop to interact with 57 AWS services using over 200 tools and local machine profiles. It supports multi-profile configurations and features a read-only safe mode by default to manage infrastructure like EC2, S3, and Lambda securely.

Enables per-profile tool filtering and enforcement for one or more upstream MCP servers, exposing only allowed tools and rejecting blocked calls, with Streamable HTTP serving and observability.

Exposes SereneDB server state as read-only MCP tools (status, storage, memory, activity, threads, profile, callgraph, host, config, and optional set_setting) so agents can query live database health and metrics with evidence-backed findings instead of viewing screenshots.

Enables an LLM to triage packet captures with nine tools that return capped summaries of conversations, talkers, protocols, DNS, HTTP, and TLS, then drill into individual packets, with every finding citing the packet number that proves it. Reads classic pcap and pcapng files using only the Python standard library, so no tshark or other external binary is required.

Enables an agent to launch or attach to a running application and profile startup phases, CPU, memory, memory bandwidth, GPU and network activity on one live timeline, capturing call stacks and hot functions. It then ties the measured hotspots to the user's own code and reports which interactions cost time or retain memory.

Enables GPU profiling and performance analysis via NVIDIA Nsight Systems, allowing agents to profile binaries and aggregate statistics for kernels, memory copies, and NVTX ranges. It supports advanced analysis through interval tree construction and structural queries on profiling reports.

Enables coding agents to trace, profile, and burn down hotspots in application and native code, GPU kernels, and inference stacks by turning explicit local artifacts or commands into bounded, provenance-typed runtime evidence. Exposes named analysis and capture tools over stdio with optional durable preservation, without requiring workspace setup or project configuration.

Enables coding agents to trace, profile, and investigate performance hotspots in application code, native code, GPU kernels, and inference stacks by coordinating local profilers, benchmark tools, trace processors, and direct capture targets. Returns bounded, typed runtime evidence with observed inputs, provenance, coverage, and limitations, all through explicit artifact paths or commands with no workspace setup required.

Enables AI agents to diagnose Linux server incidents by collecting and structuring system diagnostics from multiple servers via SSH, with tools for finding incident clusters, gathering context (memory, CPU, swap, etc.), and running arbitrary commands.

Enables coding agents to trace, profile, and burn down hotspots in application and native code, GPU kernels, and inference stacks by coordinating local profilers, benchmark tools, trace processors, and direct targets into bounded evidence with provenance and optional preservation.

Enables coding agents to coordinate local profilers, benchmark tools, trace processors, and direct targets, turning explicit artifacts or commands into bounded runtime evidence with provenance, coverage, and limitations. It exposes analysis and capture tools that help trace, profile, and burn down hotspots in application and native code, GPU kernels, and inference stacks without workspace setup or a hosted service.

Enables interaction with Oracle Cloud Infrastructure through the MCP protocol. Supports dynamic profile selection and provides 85 tools for managing compute, databases, networking, IAM, storage, load balancers, OKE, monitoring, and cost management.

A local-first MCP server that gives AI coding agents runtime visibility and AI-managed debug logging. It replaces blind print() debugging by turning runtime execution into causal chains, allowing agents to instantly locate bugs by finding missing .success events in Python and TypeScript code. Single binary with MCP, CLI, and HTTP interfaces.