realy-mcp@0.1.2
VERIFIED· not startedPublisher claims: "MCP server exposing Realy's validated table-operation retrieval agent over a customer-owned database." Observed in sandbox: no network, touches nothing outside the project, writes no memory.
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
REALY_API_KEYor--path-token-envConfiguration, not credentials: REALY_CONFIG- Where it talks to
- no vendor host named in the code
- What the honeypot saw
- no credential files read · no network
- What we could not test
- server startup · the tool list · tool behavior
Connect it with a scoped credential, under the guard. It asks for REALY_API_KEY and talks to its vendor. Give the credential to the guard, not the server: the value never enters the server's environment and only travels to the host you bind. What the tools do with a real credential was not observed.
$vet-skills run --net declared -- uvx realy-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 detectedtests/check_distribution.py:33 · Python subprocess execution detected
AST05subprocess.run([str(python), '-m', 'realy_mcp', '--version'], cwd=directory, env=clean_env, check=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.MEDIUM
Python subprocess execution detectedtests/check_distribution.py:32 · Python subprocess execution detected
AST05subprocess.run([str(cli), '--help'], cwd=directory, env=clean_env, check=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.HIGH
Hidden zero-width characters detectedsrc/realy_mcp/__main__.py:1 · Hidden zero-width characters detected — may conceal content
AST07"""Support python -m realy_mcp and the installed console script."""Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.MEDIUM
Hidden zero-width characters detectedDockerfile:1 · Hidden zero-width characters detected — may conceal content
AST07FROM python:3.12-slimFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.MEDIUM
Python subprocess execution detectedtests/check_distribution.py:30 · Python subprocess execution detected
AST05subprocess.run([str(python), '-m', 'pip', 'install', '--no-deps', '--ignore-installed', str(wheel)], check=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.LOW
Prompt injectionexamples/postgres/README.md:34 · Prompt injection — known jailbreak technique reference · informational: not an instruction file
AST01- A **ChatGPT paid plan** for the browser side (Developer Mode connectors).Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.LOW
Prompt injectiondocs/DEMO.md:171 · Prompt injection — known jailbreak technique reference · informational: not an instruction file
AST011. **Settings → Connectors → Advanced → Developer Mode** (on).Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.LOW
Prompt injectionREADME.md:190 · Prompt injection — known jailbreak technique reference · informational: not an instruction file
AST01SSE service, then enable Developer mode and create a remote MCP app/pluginFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.MEDIUM
Python subprocess execution detectedtests/test_protocol.py:256 · Python subprocess execution detected
AST05proc = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.LOW
Authorization escalation languageREADME.md:190 · Authorization escalation language · informational: not an instruction file
AST01SSE service, then enable Developer mode and create a remote MCP app/pluginFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.MEDIUM
Access to sensitive file pathstests/check_distribution.py:22 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files
AST05assert not any(Path(n).name.startswith('.env') or '__pycache__' in n for n in names)Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.MEDIUM
Python subprocess execution detectedtests/test_protocol.py:287 · Python subprocess execution detected
AST05proc = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.LOW
Authorization escalation languageexamples/postgres/README.md:164 · Authorization escalation language · informational: not an instruction file
AST011. **Settings → Connectors → Advanced → Developer Mode** (on)Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.LOW
Prompt injectiondocs/QA.md:92 · Prompt injection — known jailbreak technique reference · informational: not an instruction file
AST01historically expected `search`/`fetch`-shaped tools. Developer Mode isFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.MEDIUM
Python subprocess execution detectedtests/test_http_transport.py:138 · Python subprocess execution detected
AST05proc = subprocess.Popen(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.LOW
Prompt injectionexamples/postgres/README.md:164 · Prompt injection — known jailbreak technique reference · informational: not an instruction file
AST011. **Settings → Connectors → Advanced → Developer Mode** (on)Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.LOW
Context shift attemptREADME.md:190 · Context shift attempt — trying to change operational mode · informational: not an instruction file
AST01SSE service, then enable Developer mode and create a remote MCP app/pluginFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.MEDIUM
Tunneling service URLtests/test_http_transport.py:412 · Tunneling service URL — may route traffic to attacker infrastructure
AST07"https://abc.trycloudflare.com/mcp/t"Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.LOW
Authorization escalation languagedocs/QA.md:92 · Authorization escalation language · informational: not an instruction file
AST01historically expected `search`/`fetch`-shaped tools. Developer Mode isFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.LOW
Authorization escalation languagedocs/DEMO.md:171 · Authorization escalation language · informational: not an instruction file
AST011. **Settings → Connectors → Advanced → Developer Mode** (on).Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.LOW
Authorization escalation languageexamples/postgres/README.md:34 · Authorization escalation language · informational: not an instruction file
AST01- A **ChatGPT paid plan** for the browser side (Developer Mode connectors).Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.MEDIUM
Python subprocess execution detectedtests/check_distribution.py:34 · Python subprocess execution detected
AST05subprocess.run([str(python), '-c',Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.MEDIUM
Python subprocess execution detectedtests/check_uvx.py:36 · Python subprocess execution detected
AST05result = subprocess.run([uvx, '--from', '.', '--with', 'langchain-openai',Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.Cost to the agent
Instructions loaded
≈60 tok
1 file · 77 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 realy-mcp@0.1.2 as of 45 min ago. This is the package itself, not its dependencies.