🧱 Part of the MEOK A2A Substrate
This MCP is 1 of 12 agent-to-agent primitives. Run the whole pipeline (identity → trust → policy → firewall → rate-limit → handoff → audit → governance) as one signed endpoint for £499/mo including 100K calls — or £0.0002 per call pay-as-you-go.
👉 meok.ai/a2a — see the Substrate
Agent Prompt Injection Firewall MCP
Buy Starter — £29/mo
Signed attestations + unlimited audits + email support. 👉 Subscribe at meok.ai — instant HMAC signing key + Stripe-managed billing.
Free tier remains MIT-licensed and zero-config. Upgrade only when you need signed compliance artefacts for audit.
WAF for AI agents — block prompt injection before it reaches the LLM
Agents that blindly forward user input + retrieved documents to other agents are the #1 production AI vulnerability (OWASP LLM01). This MCP is the pre-flight gate.
By MEOK AI Labs.
Quick Install
| Client | Install |
|---|---|
| Claude Desktop | |
| Cursor | |
| VS Code | |
| Windsurf | |
| Docker | docker run -p 8000:8000 agent-prompt-injection-firewall-mcp |
| pip | pip install agent-prompt-injection-firewall-mcp |
Install
pip install agent-prompt-injection-firewall-mcp
Tools
scan_promptdefine_custom_rulelist_rulesscan_logsign_firewall_attestation
Claude Desktop
{
"mcpServers": {
"agentpromptinjectionfirewall": { "command": "agent-prompt-injection-firewall-mcp" }
}
}
Tiers
- Free — generous daily limit (100-1,000 depending on operation)
- Pro £199/mo — unlimited + signed HMAC attestations with public verify URLs — subscribe
- Enterprise £1,499/mo — multi-tenant + custom predicate DSL + SIEM webhook push — subscribe
Why this exists
The EU AI Act (Aug 2026), DORA (live), ISO 42001, and OWASP LLM01 Top-10 all demand runtime controls for agent systems — not just deployment-time audits. This MCP is that runtime control layer, emitting cryptographically signed evidence your auditor accepts.
Related MEOK A2A MCPs
agent-policy-enforcement-mcp— per-pair IAMagent-handoff-certified-mcp— signed delegation chainagent-prompt-injection-firewall-mcp— prompt injection WAFagent-rate-limiter-mcp— fleet-wide quotaagent-audit-logger-mcp— hash-chained signed loga2a-governance-bridge-mcp— map A2A to compliance frameworksmeok-attestation-verify— independent cert verifier
Wire it up — full stack
Pair this with the MEOK chain that turns one agent action into ONE signed compliance event:
- bft-progress-council-mcp — anti-loop guardrail
- agent-token-budget-mcp — hard spend cap
- agent-prompt-injection-firewall-mcp — OWASP LLM01 scan
- agent-audit-logger-mcp — hash-chained evidence
- a2a-governance-bridge-mcp — fold N attestations → 1 signed event
- agent-incident-relay-mcp — broadcast incidents to 5 regimes simultaneously
See meok.ai/mcp-stack for the full architecture and meok.ai/mcp-stack/demo for the live in-browser demo.
License
MIT — MEOK AI Labs, 2026.
Sister MCPs
Part of the MEOK A2a pack — designed to work together as a fleet. Install the whole pack with npx meok-setup --pack a2a, or pick the ones you need:
- Data Residency →
uvx agent-data-residency-mcp· PyPI · GitHub - Certified Handoff →
uvx agent-handoff-certified-mcp· PyPI · GitHub - Policy Enforcement →
uvx agent-policy-enforcement-mcp· PyPI · GitHub - Audit Logger →
uvx agent-audit-logger-mcp· PyPI · GitHub - Rate Limiter →
uvx agent-rate-limiter-mcp· PyPI · GitHub
Full catalogue + Anthropic Registry verify links: meok.ai/anthropic-registry
Protocol coverage + Universal PAYG
This MCP is part of MEOK's 47-MCP fleet that bridges every active agent-interop protocol and 30+ regulatory frameworks. See the full coverage matrix at meok.ai/protocols.
Agent interop protocols supported (8 live):
- ✅ MCP (Anthropic) — native
- ✅ A2A (Google + Linux Foundation, absorbed IBM ACP Sept 2025)
- ✅ IBM ACP — covered via A2A merge
- ◐ Stripe ACP (Agentic Commerce Protocol) — Q3 bridge via agent-commerce-protocol-mcp
- ◐ AP2 (Google Agent Payments) — partial via agent-commerce-payments-mcp
- ◐ x402 (Coinbase HTTP 402) — partial via api.meok.ai gateway
- → OASF / AGNTCY (Cisco Outshift + Linux Foundation) — Q3 bridge
- 👁 ANP (Cisco Agent Network) — watch-list
Pricing options:
| Option | Price | Best for |
|---|---|---|
| Self-host (this MCP) | £0 — MIT | Devs |
| This MCP Starter | £29/mo | One-MCP teams |
| This MCP Pro | £79/mo | Production + 24h SLA |
| Universal PAYG | £29/mo + £0.0002/call | Spiky usage across many MCPs |
| Substrate bundle (this category) | £99-£499/mo | A whole pack |
| MEOK Universe | £1,499/mo | All 47 MCPs, 500K calls |
Each tier above the free self-host adds HMAC-signed attestations verifiable at
verify.meok.ai. Linux Foundation governance on the A2A spine means EU regulated
buyers can deploy without vendor-lock-in objections.
Metadata
Release files for agent-prompt-injection-firewall-mcp 1.0.6
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| agent_prompt_injection_firewall_mcp-1.0.6.tar.gz | 226.6 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| agent_prompt_injection_firewall_mcp-1.0.6-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 237.6 kB
Release files / agent_prompt_injection_firewall_mcp-1.0.6.tar.gz
| Download URL | agent_prompt_injection_firewall_mcp-1.0.6.tar.gz |
|---|---|
| Size | 226.6 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
9c99c360f744e8c75704f1016201f1be8ae3d1edc831307b195f31204c188012
|
|
BLAKE2b-256 checksum How to use checksums |
1d53693336e332d230947fdd4db44d6a4e346ae6ccfda9c4dc6928886e65da3c
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.9.6
|
Release files / agent_prompt_injection_firewall_mcp-1.0.6-py3-none-any.whl
| Download URL | agent_prompt_injection_firewall_mcp-1.0.6-py3-none-any.whl |
|---|---|
| Size | 11.1 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
212e41740872dc23a09cdd9c65a254bacadace90b4d20896cd16d3ab0f1a25ad
|
|
BLAKE2b-256 checksum How to use checksums |
c0837bffe104b1d66f53066a7314086bde59eaa3025ee92b3af5175c56daf493
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.9.6
|