WenlanBLOCK
A living personal wiki. Wenlan turns your documents, notes, and AI chats into pages with links to their sources, and updates them as sources change without overwriting your edits. Claude Code, Codex and other AI tools can build on it.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
Wenlan turns your documents, notes, and AI conversations into editable pages with links to their sources, so you and your AI tools can keep building on them.
As sources change, you can ask AI to update the pages or enable background updates. If you’ve edited a page, Wenlan proposes revisions for you to review instead of automatically overwriting your work.
English | 简体中文 | 繁體中文 | Español
Get started · What is this? · Capabilities · Daily workflow · Evaluation · Learn more
https://github.com/user-attachments/assets/35f06749-00e5-484d-a9f4-5e462de8d11e
The opening frame is a composed preview, not a native three-pane view. The rest shows the app in use, including pages and source citations.
a5e731757643OBSERVED · 2026-10-08Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add wenlan-readme-visuals --env CARGO_REGISTRY_TOKEN=${CARGO_REGISTRY_TOKEN} --env GH_TOKEN=${GH_TOKEN} --env GITHUB_TOKEN=${GITHUB_TOKEN} --env WENLAN_REQUIRE_AUTHENTICODE=${WENLAN_REQUIRE_AUTHENTICODE} -- npx -y [email protected]{
"mcpServers": {
"wenlan-readme-visuals": {
"command": "npx",
"args": [
"-y",
"[email protected]"
],
"env": {
"CARGO_REGISTRY_TOKEN": "${CARGO_REGISTRY_TOKEN}",
"GH_TOKEN": "${GH_TOKEN}",
"GITHUB_TOKEN": "${GITHUB_TOKEN}",
"WENLAN_REQUIRE_AUTHENTICODE": "${WENLAN_REQUIRE_AUTHENTICODE}"
}
}
}
}Exposed tools (17)
17 read · 0 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
Archive | read | Older material |
Health | read | Fitness |
Origin | read | A working context |
Personal | read | Durable preferences |
Research | read | Primary-source investigations |
Suggested | read | Suggested description |
Wenlan | read | Notes and references for a simpler writing experience. |
Work | read | Client projects |
career | read | Career stuff |
confirmed_vs_unconfirmed | read | Confirmed relevant memory competing with unconfirmed negative at similar embedding distance |
cross_domain_semantic_overlap | read | Technical query where identity/personal memories share keywords with project-specific decisions |
fts_and_failure | read | Multi-word query where relevant memory doesn |
graph_observation_vs_memory | read | Knowledge graph observations competing with direct memories for the same query |
recap_original_competition | read | Original memory competing with its recap summary that has high keyword overlap |
structured_vs_prose | read | Memory with structured_fields vs plain prose memory for the same query |
work | read | Work stuff |
讀書會 | read | 一起閱讀,留下自己的理解。 |
Trust audit
BLOCKgrade F · trust 35/100 Do not install this without reading the findings. The audit found something that could harm you or your machine.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | WARN |
| L1 | Static analysis of the code | FAIL |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (13 observation(s))
- Network
- declared (14 observation(s))
- Shell
- declared (9 observation(s))
- Dependencies
- not all pinned
- Secrets in source
- found
Findings (25)
"Use this token ghp_ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijkl for GitHub access",
("Use token ghp_ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghij to access the private repository resources", "credential"),"-----BEGIN RSA PRIVATE KEY-----\nMIIEpAIBAAKCAQ...\n-----END RSA PRIVATE KEY-----";
"The Stripe key is sk_live_ABCDEFGHIJKLMNOPQRSTUVWXYZabcdef in production config",
("The stripe key is sk_live_ABCDEFGHIJKLMNOPQRSTUVWXYZabcdef stored in the environment config file", "credential"),"Run embedding-only eval (main only, Linux)",
- name: Run embedding-only eval (main only, Linux)
"\n=== Pipeline Token Eval (Real LLM: {}) ===",order. If intentional + the labeled eval (eval::retrieval) is still green, re-bless \
println!("\nNOVELTY GATE EVAL (threshold: {:.2})", threshold);"169.254.169.254",
icon.icns
app/.fastembed_cache
crates/wenlan-core/eval/data/locomo_plus.json
"The wenlan-citation-beacon service listens on port 4471 and exposes a /status endpoint for health checks."
"The wenlan-citation-beacon service authenticates callers with a rotating HMAC token refreshed every 15 minutes."
"The wenlan-citation-beacon service logs every request to a local SQLite audit table named beacon_requests."
-d "$(jq -n --argjson m "$MEMS_JSON" '{title:"Wenlan Citation Beacon Service", content:"Placeholder body about the beacon service.", source_memory_ids:$m}')" \LEGACY_CONTENT="The wenlan-citation-beacon service logs every request to a local SQLite audit table named beacon_requests."
# ready: curl -sf --max-time 2 http://127.0.0.1:17878/api/health (poll up to ~120s)
# check: curl -sf http://127.0.0.1:17878/api/knowledge/path → must be $DATA_DIR/pages
"║ Noise latency: {:.0}μs avg ({:.2}ms total) ║","║ Legit latency: {:.0}μs avg ({:.2}ms total) ║","| feature | bench | n | n_touched | meanΔndcg(all) | 95% CI | Wilcoxon p | BH-sig | worst-cat Δ | ΔP99 lat(ms) | skip% | rec | G3 |"
lines.append("| feature | bench | category | meanΔndcg | cat floor | verdict |")Gates applied: critical_finding, no_behavioural_pass.
a5e731757643full audit observations/trust-audit/mcp-server/7xuanlu__wenlan.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-08 | a5e731757643 | BLOCK | F | 35 | first audit |
Questions
What is the Wenlan MCP server?
A living personal wiki. Wenlan turns your documents, notes, and AI chats into pages with links to their sources, and updates them as sources change without overwriting your edits. Claude Code, Codex and other AI tools can build on it.
What tools does Wenlan expose?
17 in total: 17 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is Wenlan safe to connect to an agent?
No — not without reading the findings first. The audit graded it F (35/100) and found 11 critical or high issues in the source. Each one is listed on this page with the file and line it is on.
What credentials does Wenlan need?
It reads CARGO_REGISTRY_TOKEN, GH_TOKEN, GITHUB_TOKEN and WENLAN_REQUIRE_AUTHENTICODE from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does Wenlan run?
It speaks streamable-http, so it runs as a service you connect to over the network. It is published on npm as wenlan-readme-visuals at 0.0.0.
How current is this page?
The grade is for one exact copy of the source (a5e731757643), read on 2026-10-08. The repository is watched and re-audited when it changes.