This server provides a runtime firewall to detect and block prompt injection attacks in AI agent pipelines, with tiered features and compliance attestation.
Scan text for prompt injection (scan_prompt): Analyze any text (user prompts, RAG documents, tool arguments, or agent-to-agent payloads) for injection threats — returns a risk level (none, low, medium, high, critical), matched patterns, and a recommended action (allow, log, escalate, or block).
Define custom detection rules (define_custom_rule): Create tenant-specific regex-based rules (Pro+ only) with configurable actions (block, escalate, or log) to tailor detection to your use case.
List detection rules (list_rules): View all built-in and custom rules active for a specific tenant.
View scan logs (scan_log): Retrieve recent scan history with optional filtering by risk level. Free tier is limited to the last 100 entries; Pro tier is unbounded.
Generate signed attestations (sign_firewall_attestation): Emit a cryptographically signed report of firewall enforcement activity (total scans, blocks, escalations) over a specified time window — usable as compliance evidence for OWASP LLM01, EU AI Act Article 15, and ISO 42001 Annex A.5.
Enables scanning of prompts for injection attacks before they reach the LLM, with rule management and audit logging, integrated into Windsurf (Codeium).
Click on "Deploy 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., "@Agent Prompt Injection Firewall MCP scan this message for prompt injection attempts"
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.
AI agent prompt injection firewall MCP
AI agent prompt injection firewall MCP. OWASP LLM Top 10 #1 runtime guard. MIT
# Install via pip
pip install agent_prompt_injection_firewall_mcp
# Or install via Smithery
npx -y @smithery/cli@latest install agent-prompt-injection-firewall-mcp --client claudeRelated MCP server: ZugaShield
MCP protocol compliant
Easy installation
Well-documented API
Production-ready
Active maintenance
This MCP server is built with EU AI Act compliance built-in:
✅ Article 9 — Risk Management System
✅ Article 13 — Transparency & Instructions for Use
✅ Article 15 — Bias Detection & Testing
✅ Article 26 — FRIA Support (where applicable)
✅ Article 50 — AI Content Watermarking (where applicable)
Need help getting compliant? Book a free 15-min diagnostic →
Need custom development, SLA guarantees, or white-label deployment?
Pro: $99/mo — Full MCP suite + EU AI Act tracking
Enterprise: $499/mo — Custom dev + SLA + Dedicated support
View Pricing → | Contact Sales →
This server is part of the MEOK AI Labs ecosystem — 300+ MCP servers for sovereign AI governance.
Domain | Purpose |
EU AI Act compliance marketplace | |
AI safety & monitoring | |
Sovereign AI platform | |
Legacy modernization |
MIT © CSOAI-ORG
Define a tenant-specific detection rule. Pro+ only.
pattern: regex (case-insensitive)
action: block | escalate | log
| Name | Required | Description | Default |
|---|---|---|---|
| tenant_id | Yes | ||
| rule_name | Yes | ||
| pattern | Yes | ||
| action | No | escalate | |
| api_key | No |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full burden. It reveals 'Pro+ only' and pattern/action options, but fails to disclose key behaviors such as required permissions, idempotency, side effects, or the fact that it creates a rule (write operation). Incomplete.
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 very concise (two bullet points), but it sacrifices completeness by ignoring three out of five parameters. While brevity is positive, under-specification reduces usefulness for an agent. Structure is minimal.
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 5 parameters, 0% schema coverage, and an output schema, the description is severely incomplete. It does not explain required parameters, output format, or error conditions. Significant gaps remain, making it inadequate.
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 input schema has 0% description coverage. The description adds meaning for 'pattern' (regex, case-insensitive) and 'action' (block|escalate|log), but omits three required parameters (tenant_id, rule_name, api_key). Agent lacks understanding of essential inputs.
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 'Define a tenant-specific detection rule', including a specific verb (define) and resource (tenant-specific detection rule). It is distinguishable from siblings like list_rules (listing) and scan_log (scanning), making the purpose unambiguous.
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 is provided on when to use this tool versus alternatives. The description mentions 'Pro+ only' as a constraint but does not explain appropriate contexts or exclusions. No explicit reference to sibling tools or when-not-to-use.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List built-in + custom rules (if tenant_id provided).
| Name | Required | Description | Default |
|---|---|---|---|
| tenant_id | No | ||
| api_key | No |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description must fully disclose behavioral traits. It fails to mention that the tool is read-only (likely), authentication requirements (e.g., api_key), or error behavior for missing/invalid tenant_id. The minimal description does not meet the burden.
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, well-structured sentence that conveys the core functionality without superfluous words. Every word serves a purpose, and the condition is clearly expressed.
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 tool's simplicity and presence of an output schema, the description covers the basic functionality. However, it omits important context like error handling, expected input formats, and the role of api_key, leaving gaps for a simple 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?
Schema description coverage is 0%, so the description must compensate. It adds meaning to tenant_id (controls rule scope) but completely ignores api_key, leaving its purpose unexplained. This partial coverage is insufficient.
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 (list), the resource (rules), and distinguishes built-in vs custom based on tenant_id. While it differentiates from siblings like define_custom_rule, the phrasing 'if tenant_id provided' is slightly ambiguous about what is listed when the parameter is absent, preventing a perfect score.
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 explicit guidance on when to use this tool versus alternatives like define_custom_rule or scan_log. The description hints at a conditional scope but does not provide when-not criteria or compare with siblings, leaving an agent to infer usage.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent scan log. Pro tier: unbounded. Free tier: last 100.
| Name | Required | Description | Default |
|---|---|---|---|
| tenant_id | Yes | ||
| risk_filter | No | ||
| limit | No | ||
| api_key | No |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Discloses tier-based bounds on results (unbounded for Pro, last 100 for Free), which is a key behavioral trait. However, lacks details on result ordering, time range, side effects, or authentication needs.
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?
Extremely concise—two sentences front-loaded with purpose. Could add more detail without losing conciseness, but current form is efficient.
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 tool has 4 parameters and an output schema, the description is too sparse. It omits how to use risk_filter, the meaning of limit, and what the output contains. Incomplete for effective use.
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?
With 0% schema description coverage, the description should explain parameters. It does not mention tenant_id, risk_filter, limit, or api_key, leaving their roles entirely implicit.
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 returns recent scan logs and distinguishes between tier limits. However, it lacks an explicit verb like 'retrieve' or 'list', but the purpose is clear.
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. The tier limitation is noted but does not help in decision-making among siblings like list_rules or scan_prompt.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Scan a piece of text for prompt injection. Returns full decision trace.
context: where this text came from (user-prompt | rag-document | tool-arg | a2a-payload)
Returns safe, risk_level (none|low|medium|high|critical), patterns_matched
(list of rule hits), and recommended_action (allow | log | escalate | block).
| Name | Required | Description | Default |
|---|---|---|---|
| tenant_id | Yes | ||
| text | Yes | ||
| context | No | user-prompt | |
| api_key | No |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full burden. It discloses the return structure (decision trace with fields) and the context parameter's purpose. It lacks details on side effects, authentication, or rate limits, but the scanning operation is implicitly non-destructive and the output info is thorough.
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 short and front-loaded with the main action. The bullet-style list of return fields and context options is clear and efficient. However, the parameter documentation gap prevents a perfect score.
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 4 parameters (2 required), an output schema, and 4 sibling tools, the description covers the tool's purpose, output, and one parameter. But it omits explanations for 'tenant_id' and 'api_key', leaving critical gaps for a complete understanding of how to invoke 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?
Schema description coverage is 0%, requiring the description to compensate. The description only explains the 'context' parameter with its allowed values. It does not cover 'tenant_id', 'text', or 'api_key', which are not self-explanatory. Thus, the description adds limited value for parameter understanding.
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 text for prompt injection, using a specific verb and resource. It lists the return fields (safe, risk_level, patterns_matched, recommended_action) and the context parameter options, making it easy to distinguish from siblings like scan_log or define_custom_rule.
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 explains that the tool scans text and provides context options (user-prompt, rag-document, etc.), which implies usage scenarios. However, it does not explicitly state when not to use it or suggest alternatives among siblings, leaving the agent to infer without clear guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Emit a signed attestation of firewall enforcement. Evidence for OWASP LLM01 + EU AI Act Art 15 (cybersecurity) + ISO 42001 Annex A.5 (security).
| Name | Required | Description | Default |
|---|---|---|---|
| tenant_id | Yes | ||
| window_start_utc | Yes | ||
| window_end_utc | Yes | ||
| total_scans | Yes | ||
| blocks | Yes | ||
| escalations | Yes | ||
| api_key | No | ||
| No |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description must carry the burden. It does not disclose side effects, required permissions, or what 'emit signed attestation' entails (e.g., audit trail, storage).
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, but under-specified. The description is concise but lacks detail on parameters and usage.
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 8 parameters (6 required), no annotations, and an output schema not described, the description fails to cover essential context. It does not explain return value or parameter significance.
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 0%. Description does not explain any of the 8 parameters (e.g., tenant_id, window_start_utc). Agents have no information about what these fields represent.
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 states specific purpose: emitting a signed attestation of firewall enforcement, and lists compliance standards it supports. It clearly differentiates from sibling tools which handle rules and scanning.
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. The description implies use for compliance but does not specify prerequisites or exclusion conditions.
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.
v1.0.1define_custom_rulelist_rulesscan_logscan_promptsign_firewall_attestationScored across 5 tools
Each tool has a clearly distinct purpose: rule definition, listing, log viewing, prompt scanning, and attestation. There is no overlap or ambiguity between them.
Tool names follow a consistent verb_noun pattern in snake_case (e.g., define_custom_rule, list_rules, scan_log). The verbs and nouns are appropriate and predictable.
With 5 tools, the set is well-scoped for a prompt injection firewall MCP. It covers the core operations without being too sparse or overly numerous.
The set lacks update and delete operations for custom rules, which are notable gaps. While scanning and compliance are covered, rule lifecycle management is incomplete.
Security firewall for AI agents — scans MCP calls for injection, secrets, and risks.
Deterministic runtime safety for AI agents: scan PII, gate tool actions, verify LLM output.
Prompt-injection scanning and safe webpage fetching for AI agents reading untrusted content.
Prompt injection detection API for AI agents. Scan untrusted text before passing it to an LLM.
