liter-llm
One MCP server for chat, embeddings, images, speech, OCR and batch jobs across many LLM providers
Every MCP server on our list, ranked by one popularity score: GitHub stars, downloads on npm, PyPI or Docker Hub, growth over 30 days and recent activity.
702 servers, page 18 of 24.
Search capabilities in this directory
One MCP server for chat, embeddings, images, speech, OCR and batch jobs across many LLM providers
Local stdio server for a Rush monorepo: workspace details, commands, migrations, lockfile conflicts
Search, inspect and call the whole Fastly API from an assistant through three tools
Inspect, drive and debug a running Tauri desktop app during development from an MCP client
Reads and edits test cases, runs, results and milestones in a TestPlanIt test management instance
Query and, if enabled, manage XCP-ng pools, hosts, VMs and backups through Xen Orchestra
Read-only MCP access to a self-built local Parquet lake of China A-share market and company data
Checks a screenshot with local, offline OCR to confirm that expected text really shows on screen
Runs Stata code, reads datasets, stored results and graphs in a local Stata install over MCP
Lets an assistant translate a local PDF or Word document while keeping its layout, formulas and figures.
A compact Linear MCP server that packs issue search, edits, comments and raw GraphQL into one tool
Run OpenCypher queries, inspect schemas and manage graphs in a FalkorDB database
Lets an assistant hand browser tasks in plain language to Page Agent running in your own Chrome.
Local Rust index of a repo's code, docs, git history and memory, served to coding agents over MCP
Grades other MCP servers' tool catalogs for how well an AI agent can use them
Run a self-hosted L Harness LINE Official Account CRM from an MCP client: friends, tags, scenarios, broadcasts
Hands visual notes left on localhost pages in Chrome to a coding agent so it can apply them
Recommends, compares and searches agent harnesses from the curated best-of-Agent-Harnesses list
Project memory and a code-symbol graph for Claude Code, stored in your own SQLite, Postgres or MongoDB
Structural quality checks for Python code: complexity, clones, dead code, coupling and a health score
Web search, scraping, marketplace parsing and captcha solving through the 2Captcha service
MongoDB's hosted MCP endpoint for querying Atlas clusters and administering Atlas projects
Local memory for AI agents, stored in a signed append-only log, with tools to trace failures back to a cause
Typed classification, yes/no checks, scoring and ranking for coding agents via TypeSafe's Jev model
Maven and Gradle dependency lookups, upgrade checks, CVE scans and end-of-life status for JVM projects
Run a FireCMS Cloud project from a chat client: Firestore documents, collection schemas, users and settings
Local stdio bridge to MongoDB's hosted Atlas MCP server, signed in with Atlas service credentials
Local trade journal, outcome-weighted recall and hash-chained decision log for trading agents
Turns videos, screen recordings and live sessions into searchable, timestamped evidence
Agent evaluation and self-improvement harness exposed to MCP clients as scenarios, runs and judges