Skills/PyPI/massive-context-mcp

massive-context-mcp@3.0.1

CAUTION

Publisher claims: "Handle 10M+ token contexts with chunking, sub-queries, and local Ollama inference" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry PyPI (MCP server)Publisher egoughnour · joined 8 days agoInstalls 143Last detonated 3 h ago
What would fix thisWatchDispute verdict

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios) on 2026-11-06 and scored it 63/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: README links to an external installer; Direct script execution from GitHub raw URL; Privileged sudo command. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 0 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.1sprocessdependency install exit 1
0.1sprocessexec /usr/bin/date
0.1sprocessexec /usr/bin/timeout
0.1sprocessexec .venv/bin/massive-context-mcp
0.1sclaimedno tools/list reply (exit 0)
0.1sprocessscript backend runs setup only
0.1sprocessno install scripts to re-run

Static findings

HIGH
README links to an external installerREADME.md → https://ollama.com/download/Ollama-darwin.zipFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
Python subprocess execution detectedsrc/rlm_mcp_server.py:422 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
MCP server using network transport (SSE/HTTP)tests/test_ollama_setup.py:222 · MCP server using network transport (SSE/HTTP) — data sent over networkFix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.
AST04
HIGH
Direct script execution from GitHub raw URLsrc/rlm_mcp_server.py:415 · Direct script execution from GitHub raw URL — unverified code sourceFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
Python subprocess execution detectedsrc/rlm_mcp_server.py:378 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
File permission modification command.github/workflows/release.yml:364 · File permission modification command — agent changes file ownership/permissionsFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
HIGH
Privileged sudo commandsrc/rlm_mcp_server.py:1243 · Privileged sudo command — agent may execute with elevated privilegesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
File permission modification command.github/workflows/release.yml:357 · File permission modification command — agent changes file ownership/permissionsFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
HIGH
Privileged sudo commandsrc/rlm_mcp_server.py:1293 · Privileged sudo command — agent may execute with elevated privilegesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Privileged sudo command.github/workflows/release.yml:365 · Privileged sudo command — agent may execute with elevated privilegesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedsrc/rlm_mcp_server.py:433 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
LOW
Authorization escalation languageREADME.md:383 · Authorization escalation language · informational: not an instruction fileFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
MCP server using network transport (SSE/HTTP)tests/test_ollama_setup.py:231 · MCP server using network transport (SSE/HTTP) — data sent over networkFix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.
AST04
HIGH
Direct script execution from GitHub raw URLsrc/rlm_mcp_server.py:710 · Direct script execution from GitHub raw URL — unverified code sourceFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
MCP server using network transport (SSE/HTTP)tests/test_ollama_setup.py:253 · MCP server using network transport (SSE/HTTP) — data sent over networkFix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.
AST04
MEDIUM
Python subprocess execution detectedsrc/rlm_mcp_server.py:403 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
Privileged sudo commandsrc/rlm_mcp_server.py:1289 · Privileged sudo command — agent may execute with elevated privilegesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Privileged sudo command.github/workflows/release.yml:358 · Privileged sudo command — agent may execute with elevated privilegesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedsrc/rlm_mcp_server.py:361 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
MCP server using network transport (SSE/HTTP)tests/test_ollama_setup.py:269 · MCP server using network transport (SSE/HTTP) — data sent over networkFix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.
AST04

Cost to the agent

Instructions loaded
≈2,838 tok
1 file · 21 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 massive-context-mcp@3.0.1 as of 2 h ago. This is the package itself, not its dependencies.

What would make this Verified

17 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim egoughnour: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. Does not do what the description says≈ +5 on the totalIn the sandbox the skill never performed the task it claims (no call to the service it is for). Make sure the happy path runs without extra setup, or describe the real behavior.
  3. README links to an external installer≈ +4 on the totalPin versions and sources; vendor anything fetched at install time.
  4. Direct script execution from GitHub raw URL≈ +4 on the totalPin versions and sources; vendor anything fetched at install time.
  5. Privileged sudo command≈ +4 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  6. New publisher≈ +3 on the totalTime clears this on its own after 14 and 30 days. Claiming the handle (+50) is the fastest way past it.
Publish a new version to PyPI, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim egoughnourPropose a patch to the maintainer