What can you do with this server?

This server acts as a Decision Intelligence Layer, transforming economic uncertainty into actionable signals across financial domains. All outputs include confidence scores and mandatory human review thresholds for autonomous execution. * Sentiment Analysis: Analyzes market psychology (fear/greed) from raw text, outputting signals like EXECUTE, HEDGE, or DELAY. * Maritime Freight Risk: Evaluates disruption risk and True Price per corridor (e.g., Suez), with corridor-to-corridor price comparison. * DeFi Arbitrage Evaluation: Computes net return vs. flash loan cost using a 6-filter matrix to recommend action. * MEV Protection: Analyzes Uniswap V2 transactions for sandwich attack risk, returning ROI-based capital protection signals using O(1) mathematical determinism. * Agent Circuit Breaker: Terminates or monitors runaway agent processes by PID (TERMINATE_AND_REGROUP or MONITOR) to prevent token drain from infinite loops. * Cache Manager: Enables/disables semantic caching to reduce redundant vector DB calls, optimizing cost and performance. * Live Market Pulse: Access a real-time event feed for market signals. Access is available via a pay-per-decision model (L402 Lightning Network protocol) or subscription-based API keys.

Which integrations are available for this server?

Enables Google ADK agents to auto-discover and use MCP tools for economic decision signals, including market psychology, maritime freight, and DeFi arbitrage. Provides a Tool wrapper for LangChain agents to analyze market psychology, maritime freight risk, and DeFi arbitrage via the Arsenal Decision Engine.

Arsenal Decision Engine

by Faouzi122

Overview Schema Related Servers Score Discussions

Python

Remote

Arsenal Decision Engine 🛡️

The Risk-Validation Layer for Autonomous AI Agents (DeFAI)

Arsenal-Quant-Project MCP server

Method and raw results are published — backtest script · result data (180 days of Binance ETH/USDC daily closes): 🔬 Breakeven Corridor is a deterministic algebraic boundary (where IL = accumulated yield). Any position whose price ratio stays within [lower_be, upper_be] has R_net > 0 by mathematical definition — not a probabilistic model. 📐 This engine measures; it does not forecast. No predictive-accuracy figure is claimed — read the published result files and judge the method for yourself.

Mission

Transform DeFi uncertainty into deterministic, actionable risk metrics for autonomous agents. We do not run stateful trading bots or generate speculative prediction signals; we provide a stateless risk middleware layer that agents query before deploying or maintaining standard constant-product / full-range LP positions.

Built for agents. 100 free calls per IP per day — no wallet, no sign-up, custom parameters included. An L402 payment path is implemented in the gateway but is not operational in production: today, the engine is free to use.

Related MCP server: riskstate-mcp

What This Engine Does

Before an autonomous agent deploys capital or adjusts a standard constant-product / full-range LP position (such as Uniswap V2 or full-range V3), it submits the pool parameters (APY, price ratio, days held) to our API. The engine computes the exact mathematical risk, the net return ($R_{net}$), and the dynamic Breakeven Corridor bounds.

No LLMs. No hallucinations. Pure algebraic calculation.
Complexity: $\mathcal{O}(1)$ time and memory.
Latency: $< 15\text{ms}$ local execution.

Two ways to call it

1. MCP JSON-RPC — the endpoint advertised on the MCP registry

POST https://api.arsenal-quant.com/mcp

{"jsonrpc":"2.0","id":1,"method":"tools/call",
 "params":{"name":"evaluate_pool",
           "arguments":{"apy":0.20,"price_ratio":0.85,"days_held":30}}}

Standard MCP handshake: initialize → tools/list → tools/call. Available over streamable HTTP and stdio.

2. REST convenience route — no MCP client required

GET https://api.arsenal-quant.com/mcp/evaluate?apy=0.20&price_ratio=0.85&days_held=30

Both routes run the same calculation and the same quota. Note that /mcp/evaluate is GET-only: a POST to that path returns 405 Allow: GET, because JSON-RPC belongs on /mcp.

Engine Response (JSON Contract)

{
  "impermanent_loss_pct": 0.3292,
  "accumulated_yield_pct": 1.6438,
  "r_net_pct": 1.3146,
  "il_to_yield_ratio": 0.2,
  "risk_level": "LOW",
  "breakeven_corridor": {
    "lower_ratio": 0.6941,
    "upper_ratio": 1.4407,
    "interpretation": "Position remains profitable if price ratio stays within [0.6941, 1.4407]"
  },
  "inputs": {
    "apy": 0.2,
    "price_ratio": 0.85,
    "days_held": 30
  },
  "source": "Arsenal Decision Engine v2.0",
  "oracle_signature": "<HMAC-SHA256 hex — illustrative placeholder, yours will differ>",
  "layer": "FREE"
}

layer reports how the call was served: FREE while inside the free quota, PREMIUM once an L402 payment has been verified. The call shown above is served as FREE.

Access and Pricing

Free tier — evaluate_pool: 100 calls per IP per day, custom parameters included. No Lightning wallet is needed. This is the only tier currently in service.
Beyond the free quota: the gateway implements the L402 challenge and returns 402 with a WWW-Authenticate header. The payment rail is not operational in production — invoices issued today are not settleable, and no payment is expected or accepted. Treat the paid tier as announced, not available.
GET /mcp/audit/latest: 3 free calls per IP per hour; beyond that the route returns 402. That response documents the protocol; it is not a live payment path.

Python Integration Example

import urllib.request
import urllib.error
import json
import re
import os

API_URL = "https://api.arsenal-quant.com/mcp/evaluate?apy=0.20&price_ratio=0.85&days_held=30"
LNBITS_URL = "https://demo.lnbits.com"

# LNbits requires a wallet key with send permission to pay an invoice.
# Use a DEDICATED wallet funded with a small working balance, and never the key
# of a wallet holding significant funds. Keep it in the environment, never in code.
LNBITS_PAYMENT_KEY = os.getenv("LNBITS_PAYMENT_KEY")

def query_risk_oracle():
    req = urllib.request.Request(API_URL, method="GET")
    req.add_header("x-agent-id", "autonomous-lp-bot")

    try:
        with urllib.request.urlopen(req) as resp:
            return json.loads(resp.read().decode('utf-8'))
    except urllib.error.HTTPError as e:
        if e.code == 402:
            auth_header = e.headers.get("WWW-Authenticate")
            macaroon = re.search(r'token="([^"]+)"', auth_header).group(1)
            invoice = re.search(r'invoice="([^"]+)"', auth_header).group(1)

            pay_req = urllib.request.Request(
                f"{LNBITS_URL}/api/v1/payments",
                data=json.dumps({"out": True, "bolt11": invoice}).encode(),
                headers={"X-Api-Key": LNBITS_PAYMENT_KEY, "Content-Type": "application/json"}
            )
            with urllib.request.urlopen(pay_req) as pay_resp:
                preimage = json.loads(pay_resp.read().decode())["preimage"]

            retry_req = urllib.request.Request(API_URL, method="GET")
            retry_req.add_header("Authorization", f"L402 {macaroon}:{preimage}")
            retry_req.add_header("x-agent-id", "autonomous-lp-bot")

            with urllib.request.urlopen(retry_req) as final_resp:
                return json.loads(final_resp.read().decode('utf-8'))
        else:
            raise

if __name__ == "__main__":
    evaluation = query_risk_oracle()
    print(f"Risk Level     : {evaluation['risk_level']}")
    print(f"R_net          : {evaluation['r_net_pct']:+.4f}%")
    print(f"Breakeven      : [{evaluation['breakeven_corridor']['lower_ratio']}, {evaluation['breakeven_corridor']['upper_ratio']}]")

Developer Integration

Integration cookbook & MCP guides: COOKBOOK.md
MCP auto-discovery card: https://api.arsenal-quant.com/.well-known/mcp/server-card.json

Why per-call pricing is the intended model

This engine does not prevent losses, and it makes no claim about how much money it saves you. What it does is compute — deterministically, in $\mathcal{O}(1)$ — whether a position sits above or below its breakeven boundary. Each response carries an HMAC tag over the result, which lets the engine detect tampering with its own output; it is a symmetric provenance marker, not a proof a third party can verify independently.

The intended model is per-call pricing, so the cost can be budgeted like any other input. That model is not yet in service: today every call is free.

Available Tools

2 tools

evaluate_poolAInspect

Evaluate LP position risk and calculate R_net & breakeven corridor.

ParametersJSON Schema

Name	Required	Description
`apy`	Yes	Annual Percentage Yield of the pool (e.g. 0.20 for 20%)
`days_held`	No	Number of days the position has been held (default: 30)
`price_ratio`	Yes	Current price ratio compared to entry price (e.g. 0.85 for 15% price drop)

TDQS

A3.5/5.0

Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure. It does not mention whether the tool is read-only, has side effects, requires specific permissions, or how it handles inputs. The description only states the high-level function, leaving the agent without essential operational context.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, efficient sentence that captures the tool's purpose without any redundancy or filler. It is well-structured and front-loaded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool has no output schema and no annotations. The description mentions R_net and breakeven corridor but does not define these terms or indicate the output format, leaving potential gaps for an agent to understand what the tool returns.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, with each parameter having a clear description and example. The tool description adds no additional meaning about how parameters are used in the calculation, maintaining the baseline score.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool evaluates LP position risk and calculates R_net and breakeven corridor, providing a specific verb and resource. It distinguishes itself from the sibling tool get_latest_audit, which focuses on audits.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage for evaluating LP risk, but it provides no explicit guidance on when to use this tool versus alternatives or any exclusions. The context is implied but not overtly stated.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

get_latest_auditAInspect

Fetch the latest cost-intelligence and risk mitigation audit signal.

ParametersJSON Schema

Name	Required	Description	Default
No parameters

TDQS

A3.5/5.0

Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations provided, so the description must fully disclose behavior. It only says 'fetch', implying a read operation, but lacks details on authorization, rate limits, or what happens if no audit exists. Insufficient for a tool that may have side effects or constraints.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Single sentence, no redundancy. Every word is essential and the purpose is front-loaded. Highly concise.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given no output schema, the description should elaborate on what the returned audit signal contains. It names the content area (cost-intelligence and risk mitigation) but lacks detail on structure or format, leaving the agent with incomplete context.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

No parameters exist, so schema coverage is 100% by default. The baseline for 0 parameters is 4, and the description correctly avoids adding unnecessary parameter details.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Clear verb 'fetch' followed by a specific resource: 'the latest cost-intelligence and risk mitigation audit signal'. No sibling tools to distinguish from, so it effectively communicates the tool's purpose.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use this tool, prerequisites, or any context. While there are no sibling tools, the description does not help the agent decide when to invoke it beyond the bare purpose.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.

1 tool updatev0.1.5Jul 31, 2026
- Addedevaluate_pool
4 tool updatesv0.1.3Jun 30, 2026
- Removedcache_manager
- Removedcircuit_breaker
- Addedget_latest_audit
- Removedprotect_capital_from_mev

3 tool updatesv0.1.1Jun 26, 2026

Changedcache_manager2 fields changed

addedInput schema / additionalProperties
```
Added value: +false
```

addedInput schema / properties / action / description

Added value: +"ENABLE_SEMANTIC_CACHE activates the cache with a 5-minute TTL. DISABLE_SEMANTIC_CACHE flushes all cached entries and resumes live computation."

Changedcircuit_breaker4 fields changed

addedInput schema / additionalProperties
```
Added value: +false
```

addedInput schema / properties / action / description

Added value: +"The action to take. TERMINATE_AND_REGROUP kills the process immediately and logs the termination event. MONITOR observes the process without intervention and returns current resource usage statistics."

addedInput schema / properties / target_pid / description

Added value: +"The process identifier (PID) of the agent to target. Obtain this from your process manager or orchestrator. Example: '12345' or 'agent-worker-3'."

addedInput schema / properties / target_pid / examples
```
Added value: +[
+  "12345",
+  "agent-worker-3"
+]
```

Changedprotect_capital_from_mev7 fields changed

addedInput schema / additionalProperties
```
Added value: +false
```

changedInput schema / properties / attacker_weth_in / description

Previous value: -"Estimated flash-loan or capital size of the MEV searcher."New value: +"Estimated capital size of the MEV searcher (front-runner). This is the flash-loan or own-capital the attacker would use to sandwich your swap. If unknown, use 2x to 5x the victim_weth_in as a conservative estimate. Example: If victim_weth_in=10.5, a conservative attacker_weth_in would be 52.5 (5x). Typical range: 1 to 5000 WETH."

addedInput schema / properties / attacker_weth_in / examples
```
Added value: +[
+  25,
+  52.5,
+  100,
+  500
+]
```
addedInput schema / properties / attacker_weth_in / minimum
```
Added value: +0.001
```

changedInput schema / properties / victim_weth_in / description

Previous value: -"Amount of WETH the victim intends to swap."New value: +"Amount of WETH the victim (your agent) intends to swap on Uniswap V2. Must be a positive number representing the exact ETH value. Example: 10.5 means 10.5 WETH (~$26,250 at $2,500/ETH). Typical range: 0.01 to 1000 WETH."

addedInput schema / properties / victim_weth_in / examples
```
Added value: +[
+  0.5,
+  2,
+  10.5,
+  50
+]
```
addedInput schema / properties / victim_weth_in / minimum
```
Added value: +0.001
```

3 tool updatesv0.1.0Jun 26, 2026
- First observedcache_manager
- First observedcircuit_breaker
- First observedprotect_capital_from_mev

Install Server

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

B3.4/5.0

Disambiguation5/5

Only one tool exists, so there is no possibility of confusion between tools.

Naming Consistency5/5

With a single tool, naming follows a clear verb_noun pattern (get_latest_audit) and is inherently consistent.

Tool Count1/5

The server name 'Arsenal Decision Engine' suggests a broad set of capabilities, but only one trivial tool is provided, making the count highly inappropriate.

Completeness1/5

The tool surface is limited to a single fetch operation, leaving out any other actions (e.g., list, analyze, update) that would be expected from a decision engine.

Maintenance

ActivityActive

ResponsivenessUnresponsive

Resources

Need Help?

Related Servers

Related MCP Connectors

Quiver Risk Brain A
io.github.Tristan-tech-ai
Verifiable, deterministic risk math for autonomous agents; re-runnable proof on every answer.
Autonomous Agents Finance AI & Machine Learning
92
Cofferline A
com.cofferline
Treasury and risk controls for agent wallets: policies, quotes, prediction-market orders.
Finance Blockchain Autonomous Agents
471
PolyBridge A
io.github.crowdvector
Calibrated probabilistic foresight for AI agents, powered by live prediction-market signal.
Search Finance
22
scenariosim-mcp A
io.github.inity13
Deterministic what-if & scenario simulation for AI agents: projections, sensitivity & break-even.
Finance Agent Orchestration
61

Related MCP Servers

zarq-risk-intelligenceofficial
Blockchain Finance Research & Data
zarq-ai
A
license
Not graded
quality
D
maintenance
Real-time crypto risk scoring for AI agents. Trust Score, crash probability, and distance-to-default for 205 tokens. Free, no API key needed.
Updated 6 months ago (2026-03-10 15:44 UTC)
MIT
riskstate-mcp
Finance Blockchain Autonomous Agents
likidodefi
A
license
A
quality
A
maintenance
Deterministic risk governance for crypto trading agents. 5-level policy engine with position sizing, leverage limits, and trade blocking. One tool: get_risk_policy. Supports BTC and ETH.
Updated 3 months ago (2026-06-04 10:41 UTC)
1
19
1
MIT
Pharos Sentinel
Blockchain Security Autonomous Agents
mattcrypted
A
license
Not graded
quality
B
maintenance
Evaluates on-chain risk for Pharos agents before executing transactions, providing verdicts (safe/caution/dangerous) and risk-bounded execution plans via Foundry cast reads.
Updated 3 months ago (2026-06-18 08:25 UTC)
MIT No Attribution
WETH
Blockchain Cryptocurrency
ayushkumar2601
A
license
Not graded
quality
C
maintenance
Enables AI agents to analyze Ethereum wallets, simulate transactions, and draft transfers with deterministic policy and risk scoring, requiring human approval before on-chain execution.
Updated 2 months ago (2026-07-08 09:35 UTC)
2
ISC

Latest Blog Posts

Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)
By Om-Shree-0709 on July 25, 2026.
mcp
Agent Identity
OAuth 2.1
Your AI Chatbot Just Exposed Your CEO's Salary to an Intern
By Om-Shree-0709 on July 2, 2026.
Agent Identity
MCP Security
OAuth Delegation
Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)
By Om-Shree-0709 on June 30, 2026.
Agentic Ai
Prompt Injection
WebAssembly

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/Faouzi122/Arsenal-Quant-Project'

If you have feedback or need assistance with the MCP directory API, please join our Discord server

Arsenal Decision Engine 🛡️

Mission

What This Engine Does

Two ways to call it

Engine Response (JSON Contract)

Access and Pricing

Python Integration Example

Developer Integration

Why per-call pricing is the intended model

Available Tools

TDQS

TDQS

Tool Schema Changelog

TDQS

Maintenance

Resources

Related MCP Connectors

Related MCP Servers

zarq-risk-intelligenceofficial

riskstate-mcp

Pharos Sentinel

WETH

Latest Blog Posts

MCP directory API