"Buffer" matching MCP servers:

Enables AI coding assistants to capture large command outputs into an ephemeral in-memory buffer and search them via hybrid BM25 and semantic retrieval with line-level context.

MCP server for Buffer social media scheduling via the GraphQL API, enabling post creation, queue management, engagement metrics, and media uploads.

An MCP server that enables high-speed Android screenshot capture with ~50ms latency using the scrcpy frame buffer. It maintains a circular buffer for instant access to recent frames and automatically falls back to ADB when scrcpy is unavailable.

Enables real-time voice agents and streaming pipelines to smooth audio playout over volatile network conditions by providing adaptive jitter buffering and packet loss concealment. It exposes an MCP-compliant server that accepts audio frames and telemetry, returning low-latency decision and diagnostic output.

Provides adaptive jitter buffering and packet loss concealment for real-time voice streams, ensuring smooth audio playout in unstable network conditions.

A persistent, stateful MCP server that exposes a detached tmux session to clients, enabling shell command execution, terminal buffer reading, and control signal sending via JSON-RPC over stdio.

Provides comprehensive geospatial analysis capabilities through Turf.js, enabling spatial measurements, geometric operations, coordinate transformations, and geographic data processing. Supports over 100 geospatial functions including distance calculations, spatial relationships, buffer operations, and grid generation.

Enables a production-grade multimodal Google Meet copilot that captures live captions, slides, and audio into a durable local buffer, and provides an interactive dashboard, alerting, and AI-powered meeting synthesis for agents.

Enables any MCP-capable client to search Hong Kong's 1,154 official CSDI spatial datasets in English, Traditional or Simplified Chinese, retrieve them as GeoJSON, and answer questions with counts, sums and charts, interactive 2D/3D maps, feature attribute inspection, or printable static maps without an API key. Optional tools let users geocode, project or buffer geometry, render keyless Esri basemaps, and publish datasets to ArcGIS Online with their own credentials.

Enables agents to perform bounded binary-file inspection, hashing, search, and diffing within configured roots, and to preview and apply expected-byte-validated patches that produce new output copies while preserving originals. It also reads a user's existing GUI session—active buffer context, selections, and unsaved in-memory bytes—through trusted templates, with mutations to live buffers explicitly disabled.

Enables AI clients to analyze RenderDoc captures by browsing draw/dispatch events, inspecting pipeline state and shaders, and paginating vertex/constant buffer data.

Enables agents to maintain multi-tier memory across working scratchpad, dialogue buffer, and episodic stores with recency decay. Supports hybrid BM25/vector retrieval, rank fusion, graph expansion, and context reordering for optimized MCP-based memory and RAG workflows.

Captures copyable text from Claude Code terminal output before it's mangled by ANSI codes or line breaks, providing a clean clipboard buffer through a TUI.

Enables DeepSeek Harness models to directly call local ArcGIS Pro via MCP tools for reading projects, layers, GDB structures, and executing Buffer/Clip/custom ArcPy operations locally.

Enables AI agents and IDEs to classify developer intent locally in under 2 milliseconds, executing tools instantly when confident and abstaining to a cloud LLM when uncertain. It also logs outcomes to a private on-device replay buffer for continuous fine-tuning and reports lifetime token, latency, and cost savings.

Gives MCP clients tools to inspect RenderDoc .rdc captures — listing and opening frames, querying draws, pipelines, shaders, bindings, textures, buffers and pixel history, reading GPU performance counters, and exporting buffer, texture, mesh, draw-call and Unity import packages. Multiple clients can share one local GUI or headless playback backend on Windows.

Enables AI assistants to launch, drive, and verify Terminal User Interface applications by sending keystrokes and control combinations, capturing screen output, asserting text at exact coordinates, inspecting per-cell colours and cursor position, resizing live sessions, and rendering screenshots or GIFs. Supports multiple concurrent sessions in stream mode for CLI tools or buffer mode for full-screen ncurses-style apps.

A production-grade server for programmatically controlling kitty terminal instances, allowing users to launch windows, send text or key combinations, and capture scrollback buffer content. It facilitates automation workflows and command analysis by providing remote control over the kitty terminal through the Model Context Protocol.

A smart memory system for AI assistants that retrieves relevant memories using an entity graph, semantic tree, and focus buffer, with context budgeting.

Enables multi-timezone calendar event overlap resolution and deep-work buffer negotiation. It provides deterministic conflict arbitration and structured telemetry for MCP-compatible clients.

Enables MCP clients to run whole-dataset GIS operations such as buffer, clip, reproject, overlay, spatial join, dissolve, zonal statistics, and attribute selection by passing file paths in and out, so an entire dataset is processed in a single call instead of feature by feature. It works over Streamable HTTP with a shared filesystem or base64 upload/download tools for remote clients.

Machine-native GIS processing API for AI agents and developers. Convert, reproject, validate, repair, buffer, clip, dissolve, and tile vector geodata across 25 endpoints. Pay-per-use USDC on Solana Mainnet ($0.01/op). No accounts, no API keys. Remote MCP SSE.