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.
-
Durable execution and named concurrency queues for coding agents
pypi MIT -
Standalone LangChain execution recorder with durable local journaling and prepaid L402 scanner commitments.
-
Local-first cross-platform execution and research layer for AI agents with durable checkpoints and operator control.
MIT -
saigegithub.com/urmzd/saigeactive
Go SDK, CLI and MCP server for streaming agents, tools, memory, retrieval and evaluations, with pluggable model providers and durable execution.
Apache-2.0 ★ 6 -
Windows-first, resource-governed MCP runtime for local developer workstations with durable execution, scoped filesystem access, search, and developer-context backends.
Apache-2.0 ★ 1 -
Local-first cross-platform execution and research layer for AI agents with persistent PowerShell, durable checkpoints, live operator control, optional Windows UI, web research and YouTube research.
npm MIT -
tidebasegithub.com/BlueprintLabIO/tidebaseupdated this year
The open-source checkpoint layer for AI agents — checkpoints, replay, durable queues, cron, cancellation, gates, and live state, in your own Postgres.
NOASSERTION ★ 1 -
Give an autonomous agent a real email address, a webhook URL, durable memory, and the ability to wait for an event without burning tokens. Paid per call in USDC over x402.
pypi MIT -
An integrated AI platform composed from nine of these libraries: an authenticated multi-tenant API, OpenAI and Anthropic failover, streamed agent steps, an MCP server, per-tenant memory, durable multi-agent jobs with crash recovery, tracing, and evaluation.
MIT -
CONTINUUM: Verifiable semantic recovery for long-running AI agents. Semantic checkpoints (not conversation dumps), an idempotent action ledger that refuses duplicate side effects, and a hash-chained tamper-evident event log, all exposed as a deny-by-default MCP server. Framework-agnostic, Python 3.11+
Apache-2.0 ★ 27 -
Secure execution for AI agents, on any machine. Connect any MCP client to the development environment on any machine you can run a command on (even your own laptop) - no open ports, no tunnels, and your source code never leaves the machine.
AGPL-3.0 ★ 7