rawthink-mcp@2.0.1
VERIFIED· not startedPublisher claims: "Persistent memory MCP server for AI development workflows — hybrid search, knowledge graph, session lifecycle." Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Registry PyPI (MCP server)Publisher ygtalp · publishing for 215 daysInstalls 138Last detonated 1 h ago
Coverage
Not started: dependency install failed; the server itself was not observed.- Tested
- the dependency install step · every file read, file written and host contacted by what ran
- Not tested
- server startup · the tool list · tool behavior
What this means for the label: Verified here covers what ran. The server's tools were not exercised with a real credential, so nothing about their behavior is asserted; the credential summary below says what to do with that.
Before you give it your token
- It will ask for
- no credential variables read in the code
- Where it talks to
- no vendor host named in the codeAlso docker.com, ollama.com, nodejs.org, python.org, githubusercontent.com — not the publisher's domain; check what for before connecting.
- What the honeypot saw
- no credential files read · no network
- What we could not test
- server startup · the tool list · tool behavior
Connect it under the guard. Not started: dependency install failed; the server itself was not observed. The code names no credential variable; the guard pins the network to what the honeypot saw and logs every call.
$vet-skills run --net declared -- uvx rawthink-mcp
Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.
Is [email protected] safe to install?
KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios; not started: dependency install failed; the server itself was not observed) on 2026-11-15 and scored it 85/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed; the static findings and the publisher carry the rest of the score. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 0 s · 2 scenarios · 0 deviationst+CategoryObserved action
0.0sprocessno install scripts in bundle
0.2sprocessdependency install exit 1 ·
0.2sclaimednot started: dependency install failed (exit 1); the server itself was not observed
0.2sprocessscript backend runs setup only
0.2sprocessno install scripts to re-run
Static findings
MEDIUM
Python subprocess execution detectedrawthink_mcp/install.py:26 · Python subprocess execution detected
AST05subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.LOW
Instructs the agent to modify its persistent memory or instruction filesREADME.md:298 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file
AST01/rtclose export → extract entities → write handoff → update MEMORY.mdFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.LOW
Instructs the agent to modify its persistent memory or instruction filesPKG-INFO:331 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file
AST01/rtclose export → extract entities → write handoff → update MEMORY.mdFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.LOW
Instructs the agent to modify its persistent memory or instruction filesrawthink_mcp/install.py:723 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file
AST013. Handoff + MEMORY.md updateFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.MEDIUM
File permission modification commandrawthink_mcp/doctor.py:67 · File permission modification command — agent changes file ownership/permissions
AST05f"chmod u+w {vault}")Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.HIGH
Instructs the agent to modify its persistent memory or instruction files.claude/commands/rtclose.md:162 · Instructs the agent to modify its persistent memory or instruction files
AST01- New technical decisions -> add as graph entity, only 1-line summary in MEMORY.mdFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.HIGH
Direct script execution from GitHub raw URLrawthink_mcp/install.py:628 · Direct script execution from GitHub raw URL — unverified code source
AST06curl -sL https://raw.githubusercontent.com/ygtalp/rawthink-mcp/main/rawthink_mcp/rawthink-handoff.js -o ~/.claude/hooks/rawthink-handoff.jsFix: Pin versions and sources; vendor anything fetched at install time.MEDIUM
Python subprocess execution detectedrawthink_mcp/install.py:37 · Python subprocess execution detected
AST05subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.LOW
Instructs the agent to modify its persistent memory or instruction filesrawthink_mcp/install.py:879 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file
AST01- New technical decisions -> add as graph entity, only 1-line summary in MEMORY.mdFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.MEDIUM
Python subprocess execution detectedrawthink_mcp/install.py:48 · Python subprocess execution detected
AST05subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.HIGH
Instructs the agent to modify its persistent memory or instruction files.claude/commands/rtclose.md:6 · Instructs the agent to modify its persistent memory or instruction files
AST013. Handoff + MEMORY.md updateFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.HIGH
Instructs the agent to modify its persistent memory or instruction files.claude/commands/rtclose.md:158 · Instructs the agent to modify its persistent memory or instruction files
AST01### Update MEMORY.md:Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.LOW
Instructs the agent to modify its persistent memory or instruction filesrawthink_mcp/install.py:878 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file
AST01- New concepts/positions -> add as graph entities (DON'T add to MEMORY.md)Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.LOW
Instructs the agent to modify its persistent memory or instruction filesrawthink_mcp/install.py:875 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file
AST01### Update MEMORY.md:Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.HIGH
Instructs the agent to modify its persistent memory or instruction files.claude/commands/rtclose.md:161 · Instructs the agent to modify its persistent memory or instruction files
AST01- New concepts/positions -> add as graph entities (DON'T add to MEMORY.md)Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.Cost to the agent
Instructions loaded
≈832 tok
2 files · 29 in bundle
Tool list per prompt
≈0 tok
0 tools · 0 per tool
Handshake
no reply
launch to tools/list, stdio
Undocumented tools
0
description under 20 chars · avg 0
Tokens estimated at four characters each. The tool list is re-read by the agent on every turn, so it is the number to compare between servers that do the same job: ranked across the index.
Known vulnerabilities
No advisories in OSV for rawthink-mcp@2.0.1 as of 55 min ago. This is the package itself, not its dependencies.