- Conduid
- Marketplace
- #jsonl
MCP servers tagged jsonl
23 live MCP servers tagged "jsonl", ranked by trust score. Tags come from package metadata and repository topics, so this list covers servers across every category that work with jsonl.
Cozempic
Context cleaning for Claude Code — prune bloated sessions, protect Agent Teams from context loss, auto-guard with tiered pruning
Agent Inspect
Local evidence debugger and trajectory-test toolkit for TypeScript AI agents: inspect causal runs, catch wrong tool paths in CI, and share safe offline evidence.
Undatum
undatum: a command-line tool for data processing. Brings CSV simplicity to NDJSON, BSON, XML and other data files
Trail Spec
TRAIL — Tracking Records Across Isolated Logs. An open protocol for cross-MCP content tracking and deduplication.
Agentic Tracking
Call attribution for Twilio, Telnyx, Cloudflare D1, and Stripe with a TypeScript SDK, CLI, and Model Context Protocol server.
Discord CLI
Discord CLI + MCP server that runs as your own user account — read, send, search, and manage any server/DM you belong to, no bot invite. Agent-native JSON/JSONL output, SQLite + F…
Discord CLI
Discord CLI + MCP server that runs as your own user account — read, send, search, and manage any server/DM you belong to, no bot invite. Agent-native JSON/JSONL output, SQLite + F…
Promptcellar Format
Open spec for logging AI coding prompts to a JSONL file in your repo. Vendor-neutral. JSON Schema published. plf-1.
LLMmempipe
Compile noisy LLM exports (ChatGPT, Claude, Gemini) into token-efficient JSONL + Markdown for Claude Code, Projects, and agent runtimes.
MemoryPool
跨进程共享的持久记忆池 — 独立于 BIT 自带 memories.json 的中央记忆服务，CLI / HTTP API / MCP 多路接入，JSONL 落盘（BIT 生态）
Agents Traces
Ultra-fast, zero-bloat local JSONL observability and tracing for AI coding agents (MCP + CLI).
LLM Dataset Studio
Local-first text and LLM dataset curation studio for JSONL, SFT, DPO, conversations, agent traces, quality review, versioning, exports, MCP, and modular AI plugins.
Migrate
Live migration & conformance analyzer for MCP servers targeting the 2026-07-28 stateless spec. Probes stdio/HTTP servers read-only and reports findings as JSONL/Markdown.
Json Lens
MCP server and CLI that inspect and query large JSON and JSONL files with jq-like expressions - compact results, no context flooding.
Fael
Git-native memory log for AI coding agents — decisions, bugs and notes live in the repo as append-only JSONL, shared by Claude Code, Codex, OpenCode and any MCP host. No server.
Migrate
Live migration & conformance analyzer for MCP servers targeting the 2026-07-28 stateless spec. Probes stdio/HTTP servers read-only and reports findings as JSONL/Markdown.
Fastmcp Lro
Large Result Offloading for MCP servers. Writes oversized tool responses to JSONL files, returning compact descriptors with extraction recipes.
Ytb CLI
YouTube from the terminal with no API key: videos, channels, search, comments, transcripts and ranged downloads, every record saying which public surface answered.
RalfHuesing.Mcp.Observability
Unified JSONL tool-call logging and structured LLM agent feedback channel for MCP servers built on ModelContextProtocol SDK. One line of code.
Codex AI Replies CLI
从 Codex 会话记录中提取助手、工具和 MCP 事件的 CLI | A CLI for extracting assistant, tool, and MCP events from Codex session rollouts
Springofwinds Datasets
Synthetic datasets for MCP agent trajectories, function calling, and regulatory CoT
Agent Memory Site
Compile your Markdown vault into a portable agent memory. One build, every agent: Claude, Codex, Cursor, MCP, llms.txt.
Matha
No description published.