"JSON Web Tokens" matching MCP servers:

An MCP server that enables LLM coding agents to deploy web applications to AWS serverless infrastructure, supporting backend, frontend, and fullstack deployments.

Record an agent's MCP tool-call workflow once, replay it deterministically for zero tokens, and get a receipt — a snapshot-testing and deterministic-execution layer for Agent Skills.

Enables AI agents to deploy, manage, and configure web applications on sota.io, including project creation, deployment, environment variables, custom domains, and rollbacks.

Compacts noisy test, build, and cloud-log output before an AI agent reads it — dedupes repeats, collapses stack frames, folds Playwright retries, and renders CloudWatch/GCP JSON logs down to the signal. Typically 80–95% fewer tokens on failures. Tool: compact_output. Run: npx -y logslim logslim-mcp

Enables AI assistants to manage website deployments over SFTP/FTPS by listing sites, testing connections, comparing files, previewing changes with approval tokens, creating SHA-256 verified backups, and executing authorized uploads.

An MCP server for publishing static web apps via Gitea and Coolify, with scoped permissions and safety guards.

Browser acceptance testing for AI agent deliverables: verify agent output in real Chromium from JSON specs, with MCP server, visual regression, multi-browser support and GitHub Actions.

Enables AI assistants to deploy, manage, and rollback websites via the Krexel API, supporting site uploads, deploys, logs, rollbacks, environment variables, and status checks.

The Token-Curated GitLab MCP Server: 80%+ Context Window Savings. Every time your agent fetches a pipeline with other servers, it wastes 1,600 tokens of avatar URLs, internal links, and HTML fluff. With @sumirati/mcp-gitlab, that drops from 1,840 to 190 tokens.

Replay-verified minimal JSON reproductions and deterministic TypeScript/OpenAPI drift checks. Local-first CLI and MCP server.

Renders an interactive pipeline DAG and test-harness dashboard inline in MCP hosts, showing node statuses, pass rates, costs, and latency from a JSON state file.

Enables AI coding assistants to distribute iOS and Android builds to BetaDrop testers, manage share links, track releases, and manage API tokens entirely through natural language prompts.

Ship over-the-air updates for Capacitor apps from an agent: inspect the project, check native compatibility, upload web bundles, publish releases after your approval, read rollout health, and revert.

An MCP server that lets agents draw 18 diagram types from JSON (no SVG, no headless browser)

Enables AI assistants such as Claude, VS Code Copilot and Cursor to browse and modify Azure DevOps projects, work items, pull requests and pipelines through the Azure DevOps REST API, with a policy engine enforcing read-only defaults, dry-run diffs, one-time human approval tokens, project/branch scoping, secret redaction, rate limits and an audit log. Write and destructive operations stay gated behind explicit configuration and user confirmation, so agents can work with boards and pipelines without being handed full credentials.

An MCP server for Zuul CI. Debug build failures by asking questions, not clicking through web UIs. Read-only access to any Zuul instance — builds, logs, pipelines, jobs, and live status. Works with Claude Code, Claude Desktop, Cursor, and any MCP-compatible client.

A production-grade MCP server that gives AI agents secure, policy-controlled access to Coolify infrastructure, with least-privilege tokens, operation modes, allowlists, and secret redaction.

MCP server for Sqemo, a web-based ERD tool with team naming standards. 34 tools: read/edit entities, attributes, and relationships; generate physical names from a shared glossary and naming rules; SQL (7 dialects) and DBML import/export; ERD lint, diff, and ALTER generation.

Wraps Maven and Spring Boot operations for Claude Code, providing structured JSON output instead of raw build logs to save tokens and focus on code fixes.

Enables headless Blender asset QA and FBX reimport verification for game and 3D asset pipelines, checking mesh count, material count, and naming prefixes with deterministic JSON results.