MCP servers that ship as code — a repository or a package you install and run locally (usually over stdio). They have no hosted endpoint, so we cannot probe or grade them: instead each one shows its repository, install command, license, stars and when it was last updated.
Collected from GitHub repositories and npm, PyPI, Cargo, Go, Maven, NuGet and RubyGems packages tagged as MCP servers, the official MCP Registry, Docker's MCP catalog, ModelScope, Baidu MCP World, Cline and other public directories; one entry per repository. A server that also offers a hosted endpoint is listed under Remote instead. These entries are not counted in our reachability, verification or readiness statistics.
-
Semantic vector search for Engram memory — pure Go, zero CGO, MCP-native. Formerly 000Erick/synapse.
MIT ★ 1 -
MCP server for Ollama — chat, generate, embed, list models. Pure Go, zero dependencies.
★ 1 -
MCP server exposing the pure-Go aspose-pdf-foss-for-go PDF library: extract, render, merge, sign, encrypt, PDF/A
go MIT -
go-palacegithub.com/guerra/go-palaceupdated this year
Local-first memory palace for AI agents — semantic search, knowledge graph, 4-layer memory stack, MCP server. Pure Go, offline, no API keys.
MIT ★ 1 -
Fast hybrid code search for agents. Pure Go, drop-in MCP-compatible with semble.
go MIT ★ 34 -
MCP server for Go. 21 native Model Context Protocol tools that give Claude Code, Cursor and Copilot structured access to your Go AST, HTTP routes and database schema. Zero dependencies, pure standard library.
MIT ★ 3 -
A standalone Model Context Protocol server for a Dewey-classified reference library, backed by SQLite. Pure Go, no CGO.
MIT -
Open-source Go CLI for Stellar: wallets, payments, swaps, SEP-41 assets, W3C DIDs/Verifiable Credentials, ISO 20022 (pacs) reporting, a pure-Go Soroban RPC client, and an MCP server for AI assistants. Apache 2.0.
NOASSERTION ★ 2 -
Local-first, pure-Go CLI and MCP server for Midea Wi-Fi air conditioners (protocol V3)
MIT -
Task & project runtime for teams and AI agents — one Go binary as CLI, HTTP API, Web Console and MCP server, backed by pure-Go SQLite.
Apache-2.0 -
mcpkitgithub.com/adam-eques/mcpkitupdated this year
Zero-dependency Model Context Protocol (MCP) server in pure Go — stdio + HTTP transports, built-in tools (RAG, fetch, filesystem, shell, KV), SSRF guard, sandboxed filesystem, allowlisted shell. Paired with mcpc.
MIT ★ 4 -
Lightweight, single-binary geospatial data server in Go (pure Go, no CGO): MVT vector tiles, WMTS, OGC API Features, PostGIS/MBTiles/GeoJSON/GeoPackage sources, built-in MCP endpoint for LLM agents, plus spatial algorithms (shortest path, isochrone, map matching, DBSCAN).
MIT -
Design template engine + narrative engine + media pipeline. 17 AI image platforms, 4 narrative models, HTMX Web UI, MCP Server. Pure Go single binary, zero runtime deps.
go NOASSERTION ★ 3 -
agent-memgithub.com/junknet/agent-memupdated this year
High-performance, pure Go memory middleware for AI Agents (Claude/Cursor). Features active file watching, auto-distillation via LLM, and 'Single Source of Truth' versioning. Native MCP support.
★ 4 -
Embeddable time-series pattern detection engine — spike, drop, trend, anomaly, seasonality, correlation, change-point. Pure Go, in-process via chronos/embed or standalone via CLI / HTTP / MCP. Backends: memory / sqlite / postgres / mysql / libsql.
MIT ★ 2 -
A color palette toolkit. One binary, three modes: CLI, MCP, and Web UI - sharing a single pure-Go core.
MIT -
The Templetry engine: a pure Go library + CLI that renders ready-to-work repositories from compilable templates
go Apache-2.0 -
Git-native persistent memory for AI coding agents. Implements Google OKF v0.2 with sub-300µs in-memory BM25 search, embedded MCP server, and progressive disclosure. Slashes token bloat by 80% with zero external databases or dependencies. Built in pure Go.
go MIT ★ 865 -
unblinkgithub.com/ChristopherDavenport/unblinkupdated this year
Pure-Go browser for AI: fetch pages, optionally render JS (no Chromium), get clean token-budgeted Markdown over MCP
go MIT ★ 8 -
Production Pure Go Model Context Protocol (MCP) server for Manus AI v2 with Credit-Aware Capacity Pool
MIT ★ 1 -
UI structure extractor for text-only LLMs - pure Go binary, offline, CGO_ENABLED=0, MCP-native
npm MIT -
spygithub.com/tomharris/spyactive
A fast, pure-Go Slack CLI that auto-authenticates from the Slack desktop app. Read channels, send messages, manage drafts — with --json output and an MCP server mode.
MIT ★ 2 -
Session analytics MCP plugin for Claude Code. Ingests JSONL conversation logs into SQLite JSONB, tags sessions by namespace, produces structured reports with optional redaction. Pure Go, CGO_ENABLED=0.
MIT -
One pure-Go MCP server that lets an AI agent speak HTTP, GraphQL, gRPC, WebSocket, Socket.IO, SOAP, MQTT, AMQP, Kafka, NATS, STOMP, CoAP, SFTP, FTP, tus, S3, DNS, raw TCP/UDP and TLS, plus the auth those protocols use.
MIT -
Code-intelligence and evidence engine for coding agents: indexes symbols, call edges and config references, serves them over MCP and harness hooks, and proves plan claims with a verify gate. Extraction quality is measured against independent oracles. Local, pure Go.
go NOASSERTION ★ 1 -
Turns any text stream into a dated history of how its subject changed. Point it at your Claude Code, OpenCode or Codex sessions to track how you think and work, or at market news, research, or any corpus to track how it changed — raw records to observations to bi-temporal facets to narrative, with provenance, served over MCP. Single pure-Go binary.
npm MIT ★ 12 -
agentedgithub.com/frane/agentedno update data
A text editor for LLMs, not humans. Take ed, the line editor that nobody has voluntarily used since about 1975, and rebuild it for an environment where the typing user is a language model. Short verbs, line addresses, no modes, no TUI. What an editor optimises for changes when the user is the model: round trips per task, tokens per command, an editing buffer with a long memory, and an undo tree that remembers the branches the agent abandoned, because that's often where the interesting work was. ## Features - **Fewer round trips.** Read-before-Edit is unnecessary; on conflict the response carries the new content so you reconcile in one call instead of pre-reading every time. - **Branching undo.** Walked-back work stays addressable instead of being thrown away when you pick a different path. - **Three-way merge.** Concurrent agents get a structured conflict response instead of a silent overwrite. - **Atomic batches.** Multi-file refactors run all-or-nothing instead of leaving half-applied state on failure. - **Cross-file moves and regex replace as primitives.** Operations the built-in tools can't express cleanly become single calls. - **Drift detection.** External edits to an open file are folded into the tree instead of being clobbered by the next write. - **Inline diagnostics.** Type errors and lint findings surface on save, not at the next build many edits later. - **Cross-session memory.** Per-file notes persist between sessions and surface inline on the next open. - **Audit log.** Every operation recorded with actor and timestamp, so two agents in one workspace can't argue about who moved the head. ## Multi-workspace (v0.4.0) One MCP server registration handles every project you mention. Tool calls route to the workspace owning the absolute path you pass; each project gets its own SQLite, its own undo tree, its own LSP daemon — lazily spawned on first touch. Desktop hosts (Claude Desktop, Codex Desktop, Cursor) install the server once globally and use it across projects without per-project config. ## Install `ae` must be installed locally; this MCP bundle registers `ae serve` as a stdio server. ```sh brew tap frane/tap && brew install agented # or curl -sSL https://raw.githubusercontent.com/frane/agented/master/install.sh | sh ``` Pure Go, single static binary, Apache 2.0. Source: https://github.com/frane/agented
smithery -
Helm for the JVM — render charts and manage releases in pure Java, byte-for-byte compatible with `helm template`. Library, Spring Boot starter, REST API, MCP server (AI tools), and CLI.
maven Apache-2.0 ★ 7