Context7
by upstash
Feeds AI the latest docs for libraries and frameworks before it answers, so code it writes does not use outdated, removed functions.
Computer or cloud★ 64,224MITUpdated today
Install
ThoughtDAG
Overview
Description from the maker (original English)
Search local AI conversations by file or phrase and recall source turns. Four read-only tools.
PopNx MCP’s three pillars
These three are never merged into one score: opinions, measurements and popularity are different things.
- User voiceiNo reviews yetReviews open together with accounts in a later step
- Our basic checksi1 of 1 passedChecked from public information; code not scanned yet
- UsageiNot measured yet★ –
What you can do with it
We have not written a plain-language summary for this one yet. Below are the facts we read from the registry.
- Connection: Runs on your computer
- Transport: stdio
- Category: Search & AI memory
Install
Pick the AI app you use, then copy the settings.
Before you install
- Basic checks: 1 of 1 passed
- Runs on your computer with your user’s permissions (files, network, apps).
- The registry lists no key to fill in.
You need
- npmNode.js installed (for the npx command)
Which app do you use?
Pick your app above. We remember it, so next time the button says “Install in …”.
Open Claude Desktop → Settings → Developer → Edit Config, and paste this into claude_desktop_config.json
{
"mcpServers": {
"thoughtdag": {
"command": "npx",
"args": [
"-y",
"thoughtdag",
"mcp"
]
}
}
}Run this in your terminal
claude mcp add thoughtdag -- npx -y thoughtdag mcpOr copy the settings yourself
Paste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"thoughtdag": {
"command": "npx",
"args": [
"-y",
"thoughtdag",
"mcp"
]
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
Or copy the settings yourself
Paste into .vscode/mcp.json in your project
{
"servers": {
"thoughtdag": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"thoughtdag",
"mcp"
]
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
This one runs on your computer, and ChatGPT can only connect to servers on the internet. Pick another app.
Your choice stays on this device in a cookie; no account needed.
These settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.
What it can do
Runs on your computer; the tool list appears in your AI app after you install it.
Basic checksi
We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 7, 2026
- ✓ Pass
Maker matches the repo
The registry name was verified with the GitHub account chenxiachan, which owns the repo
- … Not checked yet
Still maintained
We have not read this repo from GitHub yet
- … Not checked yet
Has a licence
We have not read this repo from GitHub yet
- – Not applicable
Endpoint responds
This one runs on your computer; there is no internet endpoint
- – Not applicable
Sign-in with OAuth
Runs on your computer and uses local settings instead
- … Not checked yet
No hidden instructions in tool descriptions
Runs on your computer; we can only read tool lists from internet endpoints
Compared with others in Search & AI memoryi
- More stars than 0% of the other 7258 servers in this category
- Published to the registry more recently than 49% of the other 7258 servers in this category
- Basic checks equal to or better than 100% of the other 7258 servers in this category
Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.
Common questions
Is ThoughtDAG safe?
It passed 1 of 1 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.
What keys or codes does it need?
The registry does not list a required key, though some servers ask you to sign in on first use.
Does it run on my computer or in the cloud?
It runs on your computer. Your AI app starts it when needed, and data does not pass through the maker’s servers (unless it calls an online service itself).
Is it still maintained?
The GitHub repo last changed –, and the latest version (0.2.2) reached the registry 40 days ago.
Which apps can use it?
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. You also need Node.js on your computer.
What can I use instead?
In the same category: Context7, Codebase Memory, Exa
Alternatives
Servers in the same category from other makers, sorted by stars.
Reading a card:★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi
Codebase Memory
by DeusData
Codebase knowledge graph for AI agents — 162 languages, sub-ms queries, 99% fewer tokens.
Runs on your computer★ 48,148MITUpdated 20 days ago
Install
Exa
by exa-labs
Connect AI agents to Exa for web search, content fetching, and multi-step research.
Runs in the cloud★ 5,213MITUpdated last month
Install
README from the maker
Open the README
Copied from the maker’s repo as written. PopNx MCP has not reviewed or endorsed it. HTML, images and scripts are removed. Links lead off this site.
thoughtdag
Find the conversations that shaped a file.
npx thoughtdag why src/lib/api.tsIndexes the agent sessions already on your machine (Claude Code, Codex, DeepSeek Harness, Pi) by the files each turn read, wrote or edited, and lists those turns: when, what changed, what was asked, what the answer said about the file. Every hit links back to the conversation.
- Facts come straight off tool calls, never from free text or a model.
- Session files are read, never written. The index lives in
~/.thoughtdag(0700/0600) and can be deleted withthoughtdag purge. Δlines are observed changes;≈lines are read from the answer and are candidate explanations, not verified reasons.
thoughtdag index [--full] [--canvas <dir>]thoughtdag why [--include-read] [--all] [--limit N] [--json] thoughtdag why --check # one line, exit 0/1: is there history here? thoughtdag find " " [--in q|a|m] # where these exact words were asked, answered or attached thoughtdag recall thoughtdag status thoughtdag purge [--cache] thoughtdag mcp # the same questions as MCP tools (stdio, read-only) thoughtdag setup [mcp | rules [--remove]]
Let the agent ask on its own
thoughtdag setup mcp registers the server for Claude Code in this project's .mcp.json and for Codex in the user-level ~/.codex/config.toml; the agent then has why_check, why_file, find and recall_turn as tools. thoughtdag setup rules adds two lines to this project's CLAUDE.md and AGENTS.md — check for history before editing a file; query before explaining why code is the way it is — as a marked block, --remove takes it out. Rule changes are per project and explicit; nothing is written unless you ask.
MCP clients and directories
The server's MCP Registry name is io.github.chenxiachan/thoughtdag. A client that supports local stdio servers can start it with:
{"mcpServers": { "thoughtdag": { "command": "npx", "args": ["-y", "thoughtdag@0.2.2", "mcp"] } } }
Requires Node.js 20 or newer and supported session logs on the machine running the server. Start it in the relevant project directory so file queries use the intended workspace. Clients use different configuration formats; the example above is for clients that accept mcpServers JSON.
The four tools search and recall history; they cannot edit a canvas, modify source sessions, or replace the client's conversation. Derived indexes and caches are written under ~/.thoughtdag. Retrieved text is returned to the calling agent and may enter that agent's model context; review the client's provider settings before using private history.
Container and directory checks
The Dockerfile installs the published CLI version as a non-root stdio server. It does not copy the repository or any session data into the image. From the repository root:
docker build -f cli/Dockerfile -t thoughtdag-mcp clidocker run --rm -i --network none thoughtdag-mcp
An empty container answers MCP initialization and tools/list; history queries have no results until you explicitly provide local data. No model key, private session, or hosted endpoint is needed for the directory check.
Glama generates its own Dockerfile from the listing's Admin → Dockerfile form. Use Node.js 22 and these build steps:
["npm install --global --ignore-scripts --no-audit --no-fund thoughtdag@0.2.2"]Use these CMD arguments (Glama adds its own mcp-proxy wrapper):
["env", "THOUGHTDAG_HOME=/tmp/thoughtdag-index", "THOUGHTDAG_SESSION_ROOTS=/data/sessions", "THOUGHTDAG_CANVAS_ROOTS=/data/canvases", "THOUGHTDAG_MEMORY_ROOTS=", "thoughtdag", "mcp"]Leave placeholder credentials empty, then build and release. The repository root builds the web frontend; it does not produce dist/thoughtdag.mjs. Keep the pinned CLI version in this configuration aligned with the version you intend to list. Glama's generated image is separate from the non-root image above.
For actual local use, mount only the history directories you choose, read-only, at /data/sessions and optionally /data/canvases. The derived index is stored separately at /home/node/.thoughtdag. Query absolute artifact paths recorded in those sessions; the container's default working directory is not your host project's path. The native npx configuration above is the simpler option for project-relative queries. A cloud-hosted copy cannot see the history on your computer.
Optional Codex skill
The repository also contains a Codex skill for opening a session in the desktop app or running CLI history queries:
npx skills add chenxiachan/thoughtdag --skill thoughtdag --agent codexThis installs a skill in the current project. Opening a session needs the ThoughtDAG desktop app or its local bridge; CLI queries use the npm package. It is separate from MCP registration and does not provide a canvas-writing MCP tool.