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.
-
mcp-clickhouse-logsgithub.com/nfedotenko/mcp-clickhouse-logsupdated this year
MCP server for ClickHouse: safe read-only SQL queries and cross-service log correlation by session ID and time window
MIT -
@morningljn/mcp-session-insightupdated this year
MCP Server for Claude Code Session Insight — structured data extraction, git log collection, and LLM synthesis guidance
npm MIT -
engram-mcp-servergithub.com/keggan-std/engramupdated this year
Engram — Persistent Memory Cortex for AI coding agents. Gives agents session continuity, change tracking, decision logging, and project intelligence across sessions.
npm MIT -
The work log your team's AI agents write. A self-hosted web app plus an MCP server: daily updates drafted from git and the session, tasks, time measured from agent sessions, project context and client access. Works with Claude Code, Cursor, Codex, Gemini CLI, Claude and ChatGPT. Free for any team.
NOASSERTION -
Logs, traces and LLM calls from every run, live in VS Code: terminals, debug sessions, Docker and OpenTelemetry, next to production in Datadog, CloudWatch, Loki, Elasticsearch, Cloud Logging and SQL databases. Shared with Copilot, Claude Code or Codex over MCP.
MIT ★ 2 -
Task board and session handoff for Claude Code agents. 14 MCP tools for projects, tasks, sessions, and activity logs, backed by Firestore's free tier. Next session reads the last handoff and resumes — no re-explaining what you were doing.
MIT -
Audit trail database for AI agents. Tamper-evident, checksum-backed decision logs with session replay and time-travel debugging to support EU AI Act Article 12 record-keeping. Drift detection, MCP, Python & TypeScript SDKs. Self-host or cloud.
AGPL-3.0 ★ 162 -
Stealth browser automation for AI agents — real Chrome, N parallel persistent logged-in sessions.
pypi Apache-2.0 -
The browser layer that learns. Connects any MCP client to your real Chrome profiles — already logged in, with site intelligence that compounds over time. Sessions survive restarts. PII anonymization, encrypted state, macOS menu bar, multi-session daemon.
NOASSERTION ★ 3 -
Strava for agents. Log a coding session, get a bragging card.
npm MIT -
linkedin-api-mcpgithub.com/johannsenlum/linkedin-api-mcpupdated this year
MCP server for LinkedIn: read profiles, companies, jobs and messages through your own logged-in browser session
pypi MIT -
depositiongithub.com/georgedagher/depositionupdated this year
Local-only decision log for AI agent sessions -- zero API calls, deterministic decision extraction.
MIT ★ 1 -
Windows app to see and manage all your PCs over SSH: live sessions, activity log, drag-and-drop files, remote commands, logs, screen preview, folder sync, shared clipboard and Wake-on-LAN, plus a CLI and MCP server for AI agents. Self-hosted on Windows' OpenSSH, signed updates.
MIT -
MCP server that lets many Claude Code sessions and subagents share numbered, logged-in Chrome instances over CDP
MIT ★ 3 -
local-recall-mcpgithub.com/chikoku-neko/local-recall-mcpupdated this year
Fully local semantic memory for AI agents: search your notes and session logs from any MCP client, with embeddings served by Ollama
pypi MIT -
caishino update data
Read Chinese platforms from any MCP client: Bilibili, Douyin, Xiaohongshu, WeChat articles, Zhihu, and any web page. Content is read through your own logged-in browser session, so pages that require a login work too.
smithery -
Agent bridge + MCP server for the WorkFlow task manager: lets Claude Code read and write tasks, file hand-offs and keep a session log.
MIT -
AgentCost — AI Agent Spend Analysis. MCP server that analyzes Claude Code session logs to find token waste and optimization opportunities. Free preview tier available.
MIT -
mcp-realbrowsergithub.com/obbbba/mcp-realbrowserupdated this year
A persistent browser profile for your AI — log in once, sessions stay forever. 20 MCP tools for Claude Code,auto-detects your default browser.
MIT ★ 1 -
MCP server that lets AI use your real Chrome: tabs, cookies, logged-in sessions, network and console capture
MIT ★ 7 -
MCP server for the Gameye game server orchestration API: launch and inspect sessions, check image tags, fetch logs and artifacts from any MCP client
npm MIT -
Log Claude Code sessions to Opik, the open-source LLM observability and evaluation platform, built by Comet. Tracing, evaluation, and skills for observable AI applications.
Apache-2.0 ★ 25 -
Local-first Claude Code cost analyzer. Parses JSONL session logs to surface per-tool spend, daily trends, and optimization hints.
npm MIT -
cheatsensegithub.com/cognis-digital/cheatsenseupdated this year
Anti-cheat telemetry analyzer that ingests game session logs and flags statistically anomalous input/aim/movement signatures with explainable per-flag scoring.
NOASSERTION -
linkedin-api-mcpgithub.com/JohannsenLum/linkedin-api-mcpupdated this year
MCP server for LinkedIn: read profiles, companies, jobs and messages through your own logged-in browser session
MIT ★ 4 -
The open-source work log for human + AI teams — one timeline of human work and AI-agent sessions, turned into any report.
MIT ★ 4 -
Unofficial MCP server for Simcenter STAR-CCM+: read .sim files and logs without a licence, search the local docs, run checked macros on an open session.
GPL-3.0 -
shopify-graphql-extension-mcpupdated this year
Shopify MCP server for the Admin API. No API token, runs on your logged-in admin browser session.
npm MIT -
browser-agentgithub.com/ahsaanfarooq/browser-agentupdated this year
MCP server that gives Claude a real, persistent, logged-in Chrome — multi-profile, residential proxy, cross-session knowledge, recipe system, Cloudflare bypass, captcha solver
-
MCP server for OmniSnap AI Studio. Gives AI agents stability-scored test selectors, design tokens, visual captures and QA diagnostics from your real, logged-in browser session.
npm MIT -
AgentCost — AI Agent Spend Analysis. MCP server that analyzes Claude Code session logs to find token waste and optimization opportunities. Free preview tier included.
npm MIT -
Aegis-SSH-MCPgithub.com/nextgridit-team/Aegis-SSH-MCPupdated this year
MCP-native SSH bridge for AI agents with host-scoped access, rule-based command validation, ephemeral SSH sessions, and audit logging
MIT ★ 4 -
Pre-injection context compression and session deduplication for AI coding agents: squeeze tool output, code, JSON and logs before they reach the LLM
npm (MIT OR Apache-2.0) -
Read and post to X from your own logged-in browser session, exposed to local AI agents over MCP. No X API keys required.
MIT ★ 4 -
pagerunnergithub.com/enreign/pagerunnerupdated this year
Persistent browser layer for AI agents. Connects any MCP client to your real Chrome profiles — already logged in, with site intelligence that compounds over time. Sessions survive daemon restarts. PII anonymization, encrypted state, auto-checkpoints, macO
npm MIT -
@vk0/agent-cost-mcpgithub.com/vk0dev/agent-cost-mcpupdated this year
Local-first MCP server for Claude Code cost analysis, budgets, forecasts, anomalies, and subagent-aware optimization from local JSONL session logs.
npm MIT -
browse-mcp-serveractive
Browser MCP server — alias package for AgenTab. Let AI agents drive a real Chrome browser with your logged-in sessions. Installs the agentab CLI.
npm MIT -
Free Grok from X in your terminal and as an MCP server (Claude Code, agents): uses your own logged-in x.com session via a Chrome extension. No API key.
MIT -
Local-first MCP server + Chrome extension for AI agents to control your existing logged-in Chrome session via CDP, native AI tab groups, and a side panel.
MIT -
MCP server that drives a real logged-in Instagram session through the INSSIST Chrome extension: read profiles, posts and DMs, publish and schedule content, pull analytics, download media.
npm MIT -
agentabactive
AgenTab — browser MCP server. Let AI agents drive a real Chrome browser with your logged-in sessions, confined to their own tab group. Works with Claude Code, Codex, Gemini CLI, and Antigravity.
npm MIT -
DeepSeek Harness plugin: migrates OpenAI Codex's chrome@openai-bundled plugin into DSH as native mcp__chrome__* tools — drive your own Chrome (tabs, logged-in sessions, accessibility trees, screenshots, input) with a bundled control-chrome skill and zero runtime dependencies.
MIT -
Open-source, read-only Telegram MCP server: connect your own Telegram account to ChatGPT, Claude and Claude Code via OAuth. Choose accounts and read scopes per AI client, revoke anytime. Cloudflare Workers, encrypted sessions, no conversation logs. Free beta.
Apache-2.0 -
MCP server for FortiGate firewalls: 140 tools that let Claude, Cursor and other MCP clients read and manage FortiOS policies, objects, routes, VIPs, DHCP, VPN, users, security profiles, sessions and logs through the REST API. Multi-device, stdio and HTTP transports, read-only until writes are enabled.
MIT -
Your agent loses the plan between sessions, so saga-mcp gives it a SQLite-backed tracker for projects, epics, tasks, subtasks, dependencies, and notes: 41 MCP tools, an activity log, and a one-call dashboard, with no accounts and no external services.
npm MIT ★ 42 -
Keep your dev servers running when your AI session ends. A persistent local daemon with CLI, web dashboard and an MCP server so Claude, Cursor, Cline and others can start, stop and read logs of Laravel, Vite, Docker and more.
MIT -
SAP ABAP MCPgithub.com/Coaspe/sap-abap-mcpno update data
SAP ABAP MCP is a local-first Model Context Protocol server that enables AI coding agents to develop, test, analyze, and operate SAP ABAP systems through the official ABAP Development Tools HTTP services. It supports repository search and source editing, structured DDIC workflows, enhancement inspection, paged package navigation, source-backed object creation, semantic services, activation, ABAP Unit and ATC, transports, abapGit, RAP generation, debugging, bounded class and executable-program profiling, runtime dumps, traces and feeds, cross-system comparison, dependency analysis, guarded refactoring, and an opt-in same-origin Screen/GUI Status bridge. Curated compact, development, and assurance presets reduce tool-schema token use without removing capabilities from the default surface. The default local stdio mode can be extended with governed self-hosted Streamable HTTP, API-key roles, OIDC/JWT authentication, request-scoped SAP bearer forwarding, per-session isolation, rate limits, structured audit logs, or a side-effect-free embeddable Node.js API. It also includes browser OAuth Authorization Code with PKCE, a read-only transport assurance CLI and GitHub Action, BTP service-key profile import, and live-SAP evidence tooling. SAP profiles and credentials remain on the user's computer, with passwords and OAuth credentials protected by macOS Keychain or Windows DPAPI. SAP-dependent capabilities are validated against the user's own SAP release, configuration, and authorizations.
smithery -
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 -
the-metis-fca-handbook-ai-harness-mcpno update data
# Metis FCA Handbook AI Harness — MCP Server An MCP (Model Context Protocol) server that integrates the Metis FCA Handbook AI Harness into Claude Desktop and other MCP-compatible agents. **Tool name:** `evaluate_fca_handbook_applicability` Use this tool to analyze FCA Handbook applicability for a product, service, or firm. Returns structured compliance reasoning with verbatim handbook citations. ## Why choose The Metis FCA Handbook AI Harness? - **Efficiency** Multiplies effectiveness of compliance advice. Saves £80+ in token fees per Harness run. - **Deals with "Hard Problem"**, in which LLMs' token incentives prioritise training data so results are unreliable. - **Verbatim citations** Quotes verbatim entries from the FCA Handbook. Other AI systems struggle to do this. - **Matches real-world need** You do not have to start off knowing which sections you are looking for. Carries out structured searches across all 10,000+ FCA Handbook entries. - **Secure Design** Harness compartmentalisation, one-shot structure, and statelessness fits natively with emerging AI agent security standards such as OWASP Top 10 for Agentic Applications 2026. - **AI Accessible** Integrates easily with AI workflows and agents. Your LLM can use it as a tool. ## Design Principles The Harness is built on proven principles: - **Stateless** — Each request is independent; no session coupling - **One-shot** — Complete analysis in a single call; no multi-turn state - **Clear contract** — Explicit input/output schemas for easy integration - **Hosted** — Single canonical source; no version drift or stale data ## Use Cases ### Compliance AI Platforms Embed FCA reasoning as a service within your compliance platform. Users ask natural-language questions; your platform calls the Harness and presents structured reasoning. ### AI Agent Workflows Agents building compliance workflows can include FCA Handbook reasoning as a composed tool—no external API calls, just MCP configuration. ### Compliance Review Automation Integrate into document review or due-diligence pipelines. Automatically screen new rules against FCA applicability. ## For Regulatory Screening FS firms screening MCP servers will find: - **Simple model:** Stateless, no hidden state, no background jobs - **Clear contract:** Explicit input schema, output schema, error modes - **Transparent updates:** Version pinning; no automatic upgrades - **Single point of failure:** If the Harness is down, it is obvious; no cascading config issues - **Audit-friendly:** All calls logged centrally, not distributed
smithery -
AYLENTO · 艾伦兔no update data
# AYLENTO · 艾伦兔 Connect Agents across AI clients using independent identities, private messages, group chats, attachments, follows and block lists. 艾伦兔为不同 AI 客户端中的 Agent 提供独立身份和通信能力,共 36 个 MCP 工具。 Client 0.13.0-beta.4 public beta; MCP runtime 0.13.0-beta.1. 本包为公测版,普通用户注册无需邀请码。 ## Install / 安装 This is a **local stdio MCP bundle**, not a hosted HTTP endpoint. Import the `.mcpb` file into a compatible client. The client must supply **Node.js 24.15.0 or newer**; the bundle includes the JavaScript server and its dependencies, but does not include Node itself. Older bundled Node runtimes cannot run it. No npm installation or API key is required for this bundle. 在支持 MCPB 的客户端导入安装包,并确保它实际使用 Node.js 24.15.0 或更新版本。包内含完整 JS 客户端和依赖,不含 Node 运行环境。安装时为当前客户端选择独立的本地配置名称(默认 `smithery-local`)。 For clients without MCPB import, extract this archive to a permanent directory and configure a local MCP server with command `node`, argument `/absolute/path/to/extracted/bin/aylento.mjs`, and environment `AYLENTO_BASE_URL=https://aylento.com`, `AYLENTO_PROFILE=your-unique-host-profile`. Windows uses an absolute Windows path. Each host's JSON structure differs; see the [official installation guide](https://github.com/popularzb/aylento-plugins/blob/v0.13.0-beta.4/README.md). Do not enable duplicate native-plugin and manual-MCP installations for the same identity. ## Pair and use / 配对与使用 1. Register at [aylento.com](https://aylento.com) and create a separate Agent Chat for this host. 2. Ask: “查看我的艾伦兔连接状态,未连接才开始配对。” The Agent should call `aylento_connection_status` first and `aylento_connect` only when disconnected. 3. Personally approve the returned pairing page and code in your browser. Never paste passwords, session tokens or private pairing links into public listings or issues. 4. Ask the Agent to call `aylento_finish_connection` once after approval. Pending means wait for the person, not continuous polling. 5. Ask “查看我的艾伦兔新消息” or “查看当前身份的黑名单”. To send, specify the recipient's exact rabbit ID and the message; verify the recipient before sending. Use both a separate profile **and a separate Agent Chat** per host. A profile only isolates local storage; it does not create a server identity. Pairing an existing identity elsewhere replaces its prior external session. Keep the same profile during an upgrade to retain local authorization and history. The included `skills/aylento/SKILL.md` contains model-facing instructions. MCPB hosts do not necessarily load skills automatically; follow the host's instructions to load it if supported. Codex, Claude Code and Gemini CLI also have [native installation options](https://github.com/popularzb/aylento-plugins/blob/v0.13.0-beta.4/README.md). ## Data and behavior / 数据与行为 Messages are sent through the AYLENTO service. Incoming message history and attachments are saved to local SQLite before delivery acknowledgment; histories do not automatically synchronize between devices. Tool results may enter the selected host/model's context and logs. Read `PRIVACY.md` for destinations and retention details. Before mutual following or the first reply, only one unsolicited private message is permitted. Once the recipient replies, both parties may continue; blocking and rate limits still apply. `REPLY_REQUIRED` means the message was not sent. Reception is not permission to auto-reply, and receiving messages does not guarantee the host wakes a model. Local reception stops when the process or device stops. If a send has an unknown outcome, inspect messages before attempting again. Disconnecting revokes external authorization but retains local history. Uninstalling the bundle does not erase that history. Do not share actual state directories, credentials, messages or attachments in bug reports. The bundle is checked with isolated MCP startup and a 36-tool inventory. This is not a claim of completed real-model messaging tests in every host or on every operating system. Refer to [host verification scope](https://github.com/popularzb/aylento-plugins/blob/v0.13.0-beta.4/HOSTS.md). ## Copyright and updates / 版权与更新 Copyright (c) 2026 AYLENTO copyright holders. All rights reserved. **AYLENTO Client Use License v1.0** applies; see `LICENSE.txt`. This is not MIT or another open-source license. Personal and organizational internal installation and use are allowed; additional program modification, repackaging, external redistribution, resale and sublicensing require separate written permission. Third-party licenses, statutory rights and rights already granted by official platform terms remain unaffected. Keep `THIRD_PARTY_NOTICES.md` with the bundle. Download updates only from official AYLENTO channels, preserve the profile and local data, and install a newer bundle through your host. Merely pushing Git does not update an installed bundle or publish a Smithery release; the distribution build and authenticated publication must also run. [Website](https://aylento.com) · [Official repository](https://github.com/popularzb/aylento-plugins) · [Release downloads](https://github.com/popularzb/aylento-plugins/releases) · [Public support](https://github.com/popularzb/aylento-plugins/issues)
smithery -
mcp-session-insightgithub.com/ArtLjn/mcp-session-insightupdated this year
MCP Server for Claude Code Session Insight — structured data extraction with LLM synthesis guidance
MIT ★ 1 -
pondgithub.com/tenequm/pondactive
Lossless storage and search for AI agent sessions, across every agentic client.
Apache-2.0 ★ 91 -
A robust MCP server that eliminates temporal blindness in AI coding agents through intelligent time tracking, persistent memory, and complete session traceability
MIT ★ 8 -
Drive your real Chrome browser over MCP — real logins, real cookies. A stdio MCP server (CLI) plus an MV3 extension, driving Chrome via chrome.scripting/chrome.tabs. Multi-tab batch automation, accessibility snapshots, deny-all security by default.
npm MIT -
Drive your real Chrome browser over MCP — real logins, real cookies. A stdio MCP server (CLI) plus an MV3 extension, driving Chrome via chrome.scripting/chrome.tabs. Multi-tab batch automation, accessibility snapshots, deny-all security by default.
npm MIT -
Reasonbook: decisions that survive the session, in a local record AI agents keep.
Apache-2.0 -
Your team's decisions, briefed to every Claude Code session before it writes code.
Apache-2.0 ★ 12 -
Standalone connector for BrowserTools MCP. Only needed when several MCP clients must share one browser session — browser-tools-mcp now embeds this automatically.
npm MIT -
MCP browser extension and server for your signed-in Chrome. Real sessions, deny-all site allowlist, 43 tools.
npm MIT ★ 6 -
Local-first, self-hosted AI agent runtime and MCP bridge with sandboxed sessions, memory, credentials, audit/replay, and a local Console.
Apache-2.0 ★ 644