Skills ask-graphql-mcp
📦
ask-graphql-mcp
Content revision r1 High Risk 🌐 Network access🔑 Env variables⚙️ External commands
Analyze Web3 GraphQL Endpoints
Blockchain teams need fast answers from SubQuery and SubGraph endpoints. This skill routes natural-language questions through Ask GraphQL MCP for endpoint-aware analysis.
Supports: Claude Codex Code(CC)
Stop for confirmation before installing.
Review the plan and obtain explicit user consent before changing files.
Install with my Agent
Copy this request to your Agent. It includes the canonical Skill page and manifest.
Agent request
Review the Skillstore skill "ask-graphql-mcp" from https://skillstore.io/skills/sn-hermes-ask-graphql-mcp.md and its manifest at https://skillstore.io/api/skills/sn-hermes-ask-graphql-mcp/manifest. Verify the artifact. Stop and obtain explicit user consent before installing or changing files.Your Agent should still show its plan and request any confirmation required by the security policy.
Agent-readable resources
Use these links when an AI agent, crawler, or script needs clean context instead of reading the full page.
Test it
Using "ask-graphql-mcp". Analyze recent activity for this SubQuery endpoint.
Expected outcome:
- States the endpoint assumptions and MCP connection status.
- Summarizes active accounts, volume direction, and time window limits.
- Lists follow-up checks for schema fields or pagination.
Using "ask-graphql-mcp". My GraphQL query fails on a field name.
Expected outcome:
- Explains the likely schema mismatch in plain language.
- Suggests compatible field alternatives returned by MCP.
- Recommends a small verification step before running a full analysis.
Using "ask-graphql-mcp". Set up Ask MCP after the free quota is reached.
Expected outcome:
- Identifies paid mode as the next path.
- Describes the required gateway, endpoint header, and API key header.
- Warns the user to keep secrets scoped and avoid sharing broad credentials.
Security Audit
High Riskv5 • 7/7/2026 Open versioned report
Most static command-execution and system-reconnaissance alerts are Markdown false positives. The skill still routes data to an external MCP gateway and includes instructions that can expose API keys or private endpoint authorization headers. No prompt injection attempt was found in the reviewed files.
4
Files scanned
299
Lines analyzed
9
Review items
0
False positives ignored
Confirmed security concerns (2)
High
Chat-Based API Key Collection
The skill tells the agent to ask users to create an API key and send it in chat so execution can continue. This can expose paid service credentials in conversation logs.
Multiple files require API key requests as first or high-priority guidance, including wording that asks users to send the key here.
High
SKILL.md:54-64references/config-templates.md:17-20references/config-templates.md:36-40references/tools-and-prompts.md:20-23
Forwarding Endpoint Authorization To Third-Party Gateway
The skill sends X-ENDPOINT-AUTHORIZATION through Ask MCP when upstream endpoints are private. That can disclose private endpoint bearer tokens or session credentials to the external gateway.
The reviewed files explicitly combine private endpoint authorization headers with the external Ask MCP HTTP gateway path.
Capability review items (9)
These are real local capabilities that may be expected for this skill, so they require review but are not counted as confirmed malicious behavior.
Medium
Hardcoded URL
url: "https://ask-api.hermes-subnet.ai/mcp/graphql-agent"
The line configures a real external Ask MCP gateway. Calls can disclose user questions, endpoint URLs, and configured headers to that service.
Medium
Hardcoded URL
"url": "https://ask-api.hermes-subnet.ai/mcp/graphql-agent",
The line configures a real external Ask MCP gateway. Calls can disclose user questions, endpoint URLs, and configured headers to that service.
Medium
Hardcoded URL
"url": "https://ask-api.hermes-subnet.ai/mcp",
The line configures a real external Ask MCP gateway. Calls can disclose user questions, endpoint URLs, and configured headers to that service.
Medium
Hardcoded URL
1. Default to free gateway: `https://ask-api.hermes-subnet.ai/mcp/graphql-agent`
The line configures a real external Ask MCP gateway. Calls can disclose user questions, endpoint URLs, and configured headers to that service.
Medium
Hardcoded URL
2. Use paid gateway only when needed: `https://ask-api.hermes-subnet.ai/mcp`
The line configures a real external Ask MCP gateway. Calls can disclose user questions, endpoint URLs, and configured headers to that service.
Medium
Hardcoded URL
- Free: `https://ask-api.hermes-subnet.ai/mcp/graphql-agent`
The line configures a real external Ask MCP gateway. Calls can disclose user questions, endpoint URLs, and configured headers to that service.
Medium
Hardcoded URL
- Paid: `https://ask-api.hermes-subnet.ai/mcp`
The line configures a real external Ask MCP gateway. Calls can disclose user questions, endpoint URLs, and configured headers to that service.
Medium
Hardcoded URL
- Switch user to paid gateway `https://ask-api.hermes-subnet.ai/mcp` with `X-API-KEY`
The line configures a real external Ask MCP gateway. Calls can disclose user questions, endpoint URLs, and configured headers to that service.
Medium
Hardcoded URL
1. Paid gateway URL: `https://ask-api.hermes-subnet.ai/mcp`
The line configures a real external Ask MCP gateway. Calls can disclose user questions, endpoint URLs, and configured headers to that service.
Risk Factors
🌐 Network access (19)
agents/openai.yaml:4 agents/openai.yaml:12 references/config-templates.md:17 references/config-templates.md:19 references/config-templates.md:36 references/config-templates.md:38 SKILL.md:40 SKILL.md:52 SKILL.md:53 SKILL.md:73 SKILL.md:74 SKILL.md:94 SKILL.md:95 SKILL.md:101 SKILL.md:114 SKILL.md:115 SKILL.md:132 SKILL.md:135 SKILL.md:137
🔑 Env variables (1)
⚙️ External commands (45)
SKILL.md:18 SKILL.md:26 SKILL.md:27 SKILL.md:29 SKILL.md:32 SKILL.md:40 SKILL.md:41 SKILL.md:44 SKILL.md:45 SKILL.md:47 SKILL.md:48 SKILL.md:52 SKILL.md:53 SKILL.md:54 SKILL.md:55 SKILL.md:56 SKILL.md:58 SKILL.md:62 SKILL.md:63 SKILL.md:64 SKILL.md:73 SKILL.md:74 SKILL.md:77 SKILL.md:78 SKILL.md:79 SKILL.md:80 SKILL.md:88 SKILL.md:89 SKILL.md:90 SKILL.md:94 SKILL.md:95 SKILL.md:97 SKILL.md:101 SKILL.md:114 SKILL.md:115 SKILL.md:125 SKILL.md:126 SKILL.md:127 SKILL.md:128 SKILL.md:129 SKILL.md:132 SKILL.md:135 SKILL.md:136 SKILL.md:137 SKILL.md:139
Audited by: codex View Audit History →
Share & cite this report
Share the versioned assessment report, neutral badge, embed card, and citations. Skillstore reports evidence without deciding whether this Skill is safe.
Copy report link
https://skillstore.io/skills/sn-hermes-ask-graphql-mcp/audits/5?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_reportMarkdown badge
[](https://skillstore.io/skills/sn-hermes-ask-graphql-mcp?utm_source=security_passport_badge)HTML badge
<a href="https://skillstore.io/skills/sn-hermes-ask-graphql-mcp?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/sn-hermes-ask-graphql-mcp/security.svg" alt="Skillstore security assessment" loading="lazy"></a>Embed card
<iframe src="https://skillstore.io/embed/skills/sn-hermes-ask-graphql-mcp.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>Academic citations (APA · BibTeX · CFF)
APA citation
SN-Hermes. (2026). ask-graphql-mcp security audit report (audit version 5) [Author version unspecified]. Skillstore. https://skillstore.io/skills/sn-hermes-ask-graphql-mcp/audits/5BibTeX citation
@techreport{sn-hermes-sn-hermes-ask-graphql-mcp-2026,
author = {SN-Hermes},
title = {ask-graphql-mcp security audit report (audit version 5)},
institution = {Skillstore},
year = {2026},
number = {5},
url = {https://skillstore.io/skills/sn-hermes-ask-graphql-mcp/audits/5},
note = {Author version unspecified}
}CITATION.cff
cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "ask-graphql-mcp security audit report (audit version 5)"
version: "unspecified"
type: report
authors:
- name: "SN-Hermes"
date-released: "2026-07-07"
url: "https://skillstore.io/skills/sn-hermes-ask-graphql-mcp/audits/5"
identifiers:
- type: other
value: "skillstore:sn-hermes-ask-graphql-mcp:audit:5"
description: "Skillstore immutable audit report identifier"
Skillstore Score
Why this score Evidence Confidence: Medium 41
Architecture
85
Maintainability
87
Content
68
Community
91
Spec Compliance
What You Can Build
Analyze protocol activity
Ask for on-chain metrics, active accounts, volume trends, or staking activity from a supported GraphQL endpoint.
Debug endpoint queries
Diagnose GraphQL errors, missing fields, schema mismatches, and pagination issues with MCP-assisted reasoning.
Configure MCP access
Create free or paid Ask MCP connection guidance for a user-provided SubQuery or SubGraph endpoint.
Try These Prompts
Connect to an endpoint
Use Ask GraphQL MCP with this endpoint: <endpoint>. Confirm connectivity and summarize what data it indexes.
Inspect available data
Inspect this endpoint with Ask GraphQL MCP and describe the main entities, useful metrics, and any schema assumptions.
Debug a failing query
Use Ask GraphQL MCP to explain this query error and suggest a compatible query shape for the endpoint schema.
Design dashboard metrics
Use Ask GraphQL MCP to propose three dashboard metrics for this protocol and explain the endpoint fields needed for each metric.
Best Practices
- Use public endpoints or narrowly scoped endpoint tokens whenever possible.
- Start in free mode and switch to paid mode only after quota limits or explicit user request.
- Remove or redact secrets before sharing logs, errors, or configuration snippets.
Avoid
- Do not use broad production credentials for endpoint authorization.
- Do not use this skill for non-Web3 questions or general database work.
- Do not bypass Ask MCP with direct GraphQL execution unless the user requests it.
Frequently Asked Questions
What endpoints does this skill support?
It is designed for GraphQL endpoints used by Web3 projects, including SubQuery and SubGraph endpoints.
Does it need an endpoint URL?
Yes. It can use endpoint discovery first, but execution needs a reliable GraphQL endpoint.
Does the skill call an external service?
Yes. It routes requests through the Ask GraphQL MCP gateway.
When is paid mode used?
Paid mode is used only after free-tier quota limits or when the user explicitly requests it.
Can it debug GraphQL errors?
Yes. It can ask MCP to inspect schema issues, missing fields, and query shape problems.
Should users share secrets?
Users should avoid broad secrets and use scoped, temporary credentials when private endpoint access is required.
Developer Details
Author
SN-HermesLicense
MIT
Skillstore revision
r1
Version notice
The author did not declare a version.
Ref
f93e9bb0daca99badb6a7e574b97737155d57cb3
Maintenance freshness
7/18/2026
Usage
5 downloads · 84 views
File structure