Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@@arcwall/mcp-server scan this directory for hardcoded secrets"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Security scanning for Claude Code, Cursor, Windsurf, and any MCP-compatible AI coding tool.
Get your free API key at https://arcwall.io
Add to your MCP config:
Claude Code (~/.claude/mcp.json):
{
"mcpServers": {
"arcwall": {
"command": "npx",
"args": ["@arcwall/mcp-server"],
"env": { "ARCWALL_API_KEY": "your-key-here" }
}
}
}Cursor (.cursor/mcp.json): Same config. Windsurf: Add via MCP settings panel.
Restart your AI tool — Arcwall is ready.
Related MCP server: mycop
arcwall_scan_secrets — hardcoded credentials
arcwall_scan_mcp — MCP config vulnerabilities
arcwall_scan_agent_instructions — CLAUDE.md, .cursorrules security
arcwall_threat_model — STRIDE analysis
arcwall_check_prompt — prompt injection testing
arcwall_pre_commit — pre-commit security check
arcwall_scan_dependencies — known CVEs in packages
Ask your AI assistant:
"Scan this repo for secrets"
"Check my MCP configs for vulnerabilities"
"Is my CLAUDE.md safe?"
"Generate a threat model for this project"
"Run a security check before I commit"
"Are there vulnerable packages in this project?"
Website: https://arcwall.io
Dashboard: https://arcwall.io/app.html
Support: hello@arcwall.io
Test a system prompt for injection vulnerabilities, jailbreak susceptibility, missing guardrails, and excessive agency. Include test messages to check multi-turn vulnerabilities.
| Name | Required | Description | Default |
|---|---|---|---|
| systemPrompt | Yes | The system prompt to test. | |
| testMessages | No | Optional test messages to check multi-turn vulnerabilities. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must disclose behavioral traits. It describes inputs and purpose but omits output format, side effects, permission requirements, or any limitations (e.g., whether it modifies state). The tool likely produces a report, but this is not stated.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two concise sentences, no redundant information. Front-loaded with core purpose and immediately useful detail about test messages.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Despite being a test tool with a non-obvious return type, the description provides no information about output or how results are presented. Without an output schema, this is a significant gap for the agent to understand what to expect.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with descriptions for both parameters. The description adds context that testMessages are for 'multi-turn vulnerabilities,' which goes beyond the schema's generic 'Optional test messages to check multi-turn vulnerabilities.'
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Description explicitly states the tool tests system prompts for injection, jailbreak, guardrails, and excessive agency, which is a specific verb+resource combination. It clearly distinguishes from sibling tools like arcwall_scan_secrets or arcwall_scan_dependencies.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies when to use (for testing prompt security) but provides no explicit guidance on when not to use or alternatives. It does not mention exclusion criteria like prerequisites or limitations.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Security check before committing. Scans staged files for secrets and checks MCP configs. Returns CLEAR TO COMMIT or BLOCKED with issues to fix.
| Name | Required | Description | Default |
|---|---|---|---|
| path | No | Repository directory. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It states what is scanned and returned, but does not disclose whether the tool modifies any files, required permissions, or potential side effects.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences, no fluff, clearly structured with input, action, and output. Every sentence adds value.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the simplicity of the tool, the description covers purpose, action, and return value. Lacks error handling or prerequisites, but sufficient for a pre-commit check.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% and the parameter 'path' is described. The description adds context about 'staged files' but does not significantly elaborate beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it is a security check before committing, scans staged files for secrets and MCP configs, and returns a status. This distinguishes it from sibling tools that focus on individual scans.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies use before committing ('Security check before committing'), but does not explicitly state when to use this versus the sibling tools, nor does it provide exclusions or alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Scan agent instruction files for security vulnerabilities. Covers CLAUDE.md, .cursorrules, .windsurfrules, AGENTS.md and other formats. Detects prompt injection, sensitive data, and missing guardrails.
| Name | Required | Description | Default |
|---|---|---|---|
| path | No | Directory to search for agent instruction files. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description indicates the tool detects prompt injection, sensitive data, and missing guardrails, but lacks details on side effects, read-only behavior, or output format, which is needed given no annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences with no wasted words, front-loading the core purpose and efficiently listing covered formats and detection types.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description adequately explains purpose and scope, but lacks mention of return values or output format, which is significant since no output schema is provided.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with a single 'path' parameter described. The description adds no additional meaning or context beyond the schema, so baseline is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool scans agent instruction files for security vulnerabilities, listing specific file formats and detection types, distinguishing it from sibling tools like arcwall_scan_dependencies.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides clear context by listing covered file formats, implying usage for scanning agent instructions, but does not explicitly state when to use this tool over alternatives or when not to use it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Check dependencies for known CVEs. Scans package.json for vulnerable packages with safe version recommendations.
| Name | Required | Description | Default |
|---|---|---|---|
| path | No | Project directory to scan. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description takes the burden. It states the tool scans and recommends versions but does not disclose whether it modifies files or requires network access. The action is likely read-only, but not explicitly stated.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two concise sentences with no wasted words; the purpose is front-loaded immediately.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple scanning tool with one optional parameter and no output schema, the description adequately covers the purpose and general behavior, though it could mention the return format.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% for the single 'path' parameter, which is already described. The description adds no additional meaning beyond 'scan project directory.'
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('check dependencies for known CVEs'), specifies the resource ('package.json'), and distinguishes from sibling tools like arcwall_scan_secrets.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage for scanning dependencies but provides no explicit guidance on when to use this tool vs alternatives, nor any exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Scan MCP server configurations for prompt injection, excessive permissions, and unverified server origins. Scans .cursor/mcp.json, .vscode/mcp.json, .claude/mcp.json and other MCP config files.
| Name | Required | Description | Default |
|---|---|---|---|
| path | No | Directory to search for MCP configs. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description discloses what is scanned and for what, but lacks information on behavioral traits such as whether the tool modifies files, requires network access, or produces output. With no annotations provided, the description carries the full burden and could be more explicit about read-only nature and output format.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise with two sentences. The first sentence states the action and security checks, the second lists target config files. It is front-loaded with the core purpose. Minor improvement could be more structured formatting, but it earns its place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the low complexity (one optional parameter, no output schema), the description is somewhat complete. It explains what the tool scans and for what issues. However, it does not describe the output or results format, which would be helpful for an AI agent to understand what to expect from the tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The single parameter 'path' is described in the schema and the description provides context about the scanned files, but the description does not add significant meaning beyond the schema. With 100% schema coverage, baseline score of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool scans MCP server configurations for specific security issues like prompt injection, excessive permissions, and unverified origins. It also lists the specific config files it scans, distinguishing it clearly from sibling tools that handle other security scanning tasks.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage for scanning MCP configs but provides no explicit guidance on when to use this tool versus alternatives like arcwall_scan_dependencies or arcwall_scan_secrets. No when-not or context for choosing this tool.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Scan workspace for hardcoded API keys, passwords, private keys, tokens, and credentials. Run before committing or deploying.
| Name | Required | Description | Default |
|---|---|---|---|
| path | No | Directory to scan. Defaults to current directory. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. It only says 'scan workspace,' implying a read-only operation, but does not disclose whether it modifies files, reports results, or any side effects. Important behavioral traits like output format or error behavior are missing.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
A single sentence that is front-loaded with the action and resource. No extraneous information; every word serves a purpose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple tool with one optional parameter and no output schema, the description covers core function and usage context. However, it fails to explain return values or output behavior, which is necessary for completeness given the lack of an output schema.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100% (parameter 'path' is described as 'Directory to scan. Defaults to current directory.'). The description adds no additional meaning beyond the schema, so baseline 3 applies.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool scans for hardcoded secrets (API keys, passwords, etc.) in the workspace, using a specific verb and resource. It implicitly distinguishes from siblings like arcwall_check_prompt and arcwall_pre_commit by focusing on secret scanning, but does not explicitly differentiate.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Provides explicit when-to-use guidance: 'Run before committing or deploying.' However, it lacks exclusions, alternatives, or context about when not to use this tool versus sibling tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Generate a STRIDE threat model for the current codebase. Identifies trust boundary gaps, authorization issues, data flow exposures, and architectural risks. Results saved to Arcwall dashboard.
| Name | Required | Description | Default |
|---|---|---|---|
| path | No | Directory to analyze. | |
| repoName | No | Repository or system name. | |
| mode | No | code: scan codebase. design: analyze architecture. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description must disclose behavioral traits. It mentions results saved to dashboard but doesn't describe side effects, access requirements, or execution time. For a tool that likely reads code, this is insufficient.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences, front-loaded with primary action. No redundant information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With 3 parameters and no output schema, description covers basic purpose but lacks detail on parameter interplay (e.g., how path and repoName relate, mode behavior). Adequate but not thorough.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% for all 3 parameters. Description adds no additional context beyond schema. Baseline score satisfied.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Clearly states it generates a STRIDE threat model for the codebase, listing specific risk types and output destination. Distinguishes from sibling tools (e.g., arcwall_scan_secrets) which are more specific scanning tools.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives like arcwall_scan_dependencies or arcwall_scan_secrets. Agent must infer from tool names.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
v1.0.1arcwall_check_promptarcwall_pre_commitarcwall_scan_agent_instructionsarcwall_scan_dependenciesarcwall_scan_mcparcwall_scan_secretsarcwall_threat_modelEach tool targets a distinct security concern: prompt injections, pre-commit checks, agent instructions, dependencies, MCP configs, secrets, and threat modeling. No two tools overlap in purpose.
All tools share the 'arcwall_' prefix and use descriptive verb-noun or noun phrases. Minor inconsistency: 'check' vs 'scan' verbs, but overall pattern is clear and predictable.
Seven tools cover the essential scanning and security assessment needs for a development workflow. The count is well-scoped without being too few or too many.
Covers major security scanning areas (prompts, secrets, dependencies, configs). Minor omission might be runtime monitoring, but the set is fairly complete for its stated purpose.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Zero-config MCP security scanner for AI-generated apps. 25K+ vulnerability patterns.
Threat modeling, code/cloud/pipeline scanning, shadow-AI discovery, compliance checks and fixes.
Zero-install security baseline for AI coding agents — OWASP/CWE-cited rules over MCP.
Security reviews for coding agents: diffs checked against your org policy and live infrastructure.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/rom-baro/arcwall-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server