ThoughtDAG
NPM · THOUGHTDAG · SCANNED SEP 28
Search local AI conversations by file or phrase and recall source turns. Four read-only tools.
Available components
How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →
Supply Chain Security100
- No malware found by supply-chain analysis.Pass
- No known CVEs affecting this package version or its production dependencies.Pass
- No install/post-install scripts declared.Pass
- No production dependencies, so there is no dependency health to assess. View diagnostics → Pass
Provenance & Transparency97
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Cryptographically verified build provenance (signed, bound to chenxiachan/thoughtdag). View diagnostics → Pass
- Clear OSI-approved license (MIT).Pass
- Actively maintained (last published 0 days ago).Pass
- Disclosure check failed: no security disclosure policy was found in the source repository. See how to fix → Fail
Schema Quality & AI Usability69
- AI-judged instruction clarity (good).Pass
- Tool/resource definitions use about 310 tokens (~77/item across 4 items; 4 tools + 0 resources), lean.Pass
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management0
- Stability not yet verified: not enough scan history yet (needs a 30-day window).Unverified
Tool Coverage78
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 33% of tool parameters carry a description.Partial
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 4 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 4 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Unverified: 1 category
A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.
How do I install the ThoughtDAG MCP server?
ThoughtDAG runs locally as an npm package, launched with npx -y thoughtdag. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
npm · thoughtdag
claude mcp add chenxiachan-thoughtdag -- npx -y thoughtdag
{
"mcpServers": {
"chenxiachan-thoughtdag": {
"command": "npx",
"args": [
"-y",
"thoughtdag"
]
}
}
} {
"servers": {
"chenxiachan-thoughtdag": {
"command": "npx",
"args": [
"-y",
"thoughtdag"
]
}
}
} codex mcp add chenxiachan-thoughtdag -- npx -y thoughtdag
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"chenxiachan-thoughtdag": {
"type": "local",
"command": [
"npx",
"-y",
"thoughtdag"
],
"enabled": true
}
}
} openclaw mcp add chenxiachan-thoughtdag --command npx --arg -y --arg thoughtdag
mcp_servers:
chenxiachan-thoughtdag:
command: "npx"
args: ["-y", "thoughtdag"] {
"McpServers": {
"chenxiachan-thoughtdag": {
"Transport": "stdio",
"Command": "npx",
"Arguments": [
"-y",
"thoughtdag"
]
}
}
} assistant mcp add chenxiachan-thoughtdag -t stdio -c npx -a -y thoughtdag
{
"mcpServers": {
"chenxiachan-thoughtdag": {
"command": "npx",
"args": [
"-y",
"thoughtdag"
]
}
}
} Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 27 Sept 26 78
First indexed and scored.
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 28 Sept 2026 · Analysed npm/thoughtdag@0.2.2
Provenance Verified
A signed build attestation was found and verified, binding this exact artifact to the source repository it claims to come from.
| Result | Verified |
|---|---|
| Ecosystem | npm |
| Reason | Verified |
| Discovered via | Registry attestation endpoint |
| Source repo | chenxiachan/thoughtdag |
| Certificate issuer | https://token.actions.githubusercontent.com |
| Certificate SAN | https://github.com/chenxiachan/thoughtdag/.github/workflows/publish-cli.yml@refs/heads/main |
| Rekor log index | 2980245472 |
| Predicate type | SLSA build provenance https://slsa.dev/provenance/v1 |
| Subject digest | sha512:4aacc0a93712519df6bec131f993815a727bc4a222ccac68fe3d6a12b85d97d979d439f02c6d9ead18db8340dd18c335e2ee1532a58e4d4a3a69cde6d |
Background: How many MCP packages publish verified provenance →
Dependencies 0 packages
| Packages resolved | 0 |
|---|---|
| Tree resolution | Complete |
Background: SBOMs and build attestations, explained →
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
find ~82
Where these exact words were asked (Q), answered (A) or attached (M) across local sessions, canvases and the memories Claude Code and Codex keep for themselves. Exact, case-insensitive match; every hit is a verbatim snippet with a pointer.
| Name | Type | Req | Description |
|---|---|---|---|
| in | string | – | – |
| limit | number | – | – |
| phrase | string | yes | – |
No output schema declared.
No examples provided.
recall_turn ~57
One turn in full — the question, the answer, the tool calls with their diffs — by session id (or prefix) and turn number as shown by why_file.
| Name | Type | Req | Description |
|---|---|---|---|
| session | string | yes | – |
| turn | number | yes | – |
No output schema declared.
No examples provided.
why_check ~58
Cheap first question before editing a file: does this artifact have any history in local agent sessions? One line; history true/false.
| Name | Type | Req | Description |
|---|---|---|---|
| path | string | yes | file path (absolute or relative to cwd), URL, or arxiv:<id> |
No output schema declared.
No examples provided.
why_file ~113
The turns across local Claude Code, Codex, DeepSeek Harness, Pi and ThoughtDAG sessions that touched a file, URL or paper: when, what changed (Δ, observed), what was asked, what the answer said about it (≈, a candidate explanation, not a verified reason). Each hit carries a deep link.
| Name | Type | Req | Description |
|---|---|---|---|
| include_read | boolean | – | also list turns that only read it (default false) |
| limit | number | – | max hits (default 10) |
| path | string | yes | – |
No output schema declared.
No examples provided.
What is the ThoughtDAG MCP server?
ThoughtDAG is an MCP server listed in the public MCP registry as io.github.chenxiachan/thoughtdag. Search local AI conversations by file or phrase and recall source turns. Four read-only tools. This page covers its npm package (thoughtdag).
Is the ThoughtDAG MCP server safe to use?
ThoughtDAG scores 78 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 28 September 2026. It declares no install or post-install scripts. Its build provenance is signed and verified. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the ThoughtDAG MCP server expose?
ThoughtDAG exposes 4 tools: why_check, why_file, find, recall_turn. Their descriptions and schemas cost roughly 310 tokens of context every time the server is loaded.
Is the ThoughtDAG MCP server still maintained?
ThoughtDAG is still listed as active in the MCP registry. We last reached this channel on 28 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.
What licence is the ThoughtDAG MCP server under?
ThoughtDAG declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.