solidity-sentinel
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., "@solidity-sentinelaudit this Uniswap V2 pair contract for flash loan vulnerabilities"
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.
solidity-sentinel π‘οΈ
Static security audit for Solidity smart contracts β for AI agents and developers.
solidity-sentinel is an MCP server and a pay-per-call x402 HTTP API. Paste a contract's source (or the raw deployed bytecode of an unverified contract) and get a CRITICAL / HIGH-RISK / REVIEW / LOW-RISK / CLEAN verdict with a 0β100 risk score and, in the deep tier, a full finding list β each with its exact line, the sourceβsink dataflow, a code-evidence snippet, the SWC + CWE id, a confidence score, an exploit explanation, and a concrete fix.
β οΈ Heuristic static screen, not a formal audit. It pattern-matches source structure and dataflow; it cannot prove a contract safe and can miss novel bugs. Absence of a finding is not a guarantee. Always pair with tests, fuzzing and a manual review before risking funds.
Why it exists (the moat)
An AI agent asked to "check this contract for bugs" makes one pass and produces a few regex-grade observations. A real review is the accumulated depth of an auditor working through the whole surface. solidity-sentinel encodes that depth:
A flow-sensitive taint/dataflow engine (CFG-based). It tracks attacker-controlled values (function params,
msg.sender, external-call returns) into dangerous sinks (delegatecall/call targets,selfdestruct, transfer amounts, array indices,sstoreslots). It does not walk statements linearly β it builds a control-flow graph and runs a forward dataflow with a JOIN at branch confluences (a value tainted on any path is tainted after the merge), loop fixpoints (taint a loop body creates reaches code after the loop), and revert/early-return guards (if (msg.sender != owner) revert();makes the fall-through path trusted). A guard on one branch does not sanitise the merge. This catchesif (g) { t = userInput; } else { t = safe; } β¦ t.delegatecall(d)and stays silent on owner-guarded / immutable-target code β killing both false negatives and false positives.Multi-level interprocedural + cross-contract. Taint follows internal call chains several hops deep (
entry β mid β inner β sink) and across contracts in the same project (router.run(tainted)into another contract's delegatecall), recording the full call/contract chain in the evidence.High-value DeFi families where the money is: flash-loan-manipulable accounting, ERC-4626 first-depositor / share inflation, read-only reentrancy (stale view price during a transfer), callback-based reentrancy (ERC-777/1363 + flash-loan callbacks), MEV / sandwich exposure (no slippage bound), TWAP-window manipulation, unsafe liquidation, governance/timelock bypass, EIP-2612 permit replay, spot-price oracles.
Deployed-bytecode screening for unverified contracts (no source): it disassembles runtime bytecode and flags
DELEGATECALL/SELFDESTRUCTcapabilities and calldata-controlled delegatecall takeover at the EVM level β ground truth a misleading source comment can't hide.The classics, done right: a tokenizer that isn't fooled by strings/comments, a parser that knows each function's visibility/mutability/modifiers, CEI ordering dataflow, interprocedural reentrancy, and version-aware arithmetic.
The engine ships with 227 automated tests, including a 153-case calibration corpus modelled on real incidents (TheDAO, Parity, bZx, Cream, Euler, Beanstalk, Nomad, Lendf.me, Wormhole, Ronin, Multichain, Mango, Rari, Visor, Qubit, BadgerDAO, KyberSwap, Sentiment, Penpie, Sushi RouteProcessorβ¦) and audited-clean contracts. Measured on that corpus: 100% recall, 0 false positives β every must-flag fires, and safe CEI code, guarded reentrancy, immutable-target / beacon-proxy delegatecall, revert-guarded sinks, bounded indices, complete EIP-712 permits, slippage-bounded swaps, windowed TWAPs and .call text inside comments/strings are not flagged. A coverage drift-guard test asserts every detector id the engine fires is documented in the SWC/severity/confidence map β the docs can't silently fall out of sync with the code.
Related MCP server: Smart Contract Security Analyzer
What it analyses (taint engine + 12 detector families)
Family | Examples it catches |
π Dataflow / taint (flow-sensitive) | attacker-controlled value β delegatecall/call target, |
π Reentrancy | classic ETH reentrancy (CEI violated), cross-function reentrancy on shared state, read-only reentrancy (stale view price), callback-based (ERC-777/1363 + flash-loan callbacks), ERC-777/721/1155 receiver-hook reentrancy (no raw |
π Access control | unprotected |
π¦ DeFi families | flash-loan-manipulable accounting, ERC-4626 first-depositor inflation, MEV / sandwich (no slippage bound), TWAP-window manipulation, unsafe liquidation (no health check), governance without timelock, EIP-2612 permit missing deadline/nonce |
β Arithmetic | pre-0.8 overflow/underflow without SafeMath, |
βοΈ Low-level calls |
|
π² Randomness | weak randomness from |
π Oracle | spot-price (getReserves/ |
βοΈ Signatures |
|
β¬οΈ Proxy / upgradeability | constructor-init in upgradeable contracts, UUPS without |
π§± DoS | unbounded loops, push-payment loops a single revert can brick, O(n) array shifting |
β ERC-compliance & gas |
|
𧬠Deployed bytecode | disassembles runtime bytecode of unverified contracts; flags |
Each finding is mapped to its SWC and CWE id. SWC coverage (documented in detectors/coverage.ts and asserted in sync by coverage.test.ts): SWC-100, 101, 102, 103, 104, 105, 106, 107, 112, 114, 115, 116, 117, 118, 120, 121, 128, 132, 133 β plus the DeFi/dataflow families that have no SWC number (oracle manipulation, flash-loan accounting, ERC-4626 inflation, read-only reentrancy, MEV/sandwich, TWAP-window, governance timelock). Severity and confidence are calibrated per detector and further adjusted at runtime by path guards, interprocedural depth and cross-contract distance.
Tiers
Free | Deep (paid) | |
Detectors | 4 high-signal | flow-sensitive taint engine + all 16 families + bytecode mode |
Output | verdict + risk score + finding counts + top issue titles | every finding: line, the sourceβsink flow, evidence, SWC/CWE, confidence, exploit reasoning, fix, + per-contract surface inventory |
Runs | locally in the installed package | server-side, behind payment |
Cost | free (rate-limited) | $0.05 USDC per call via x402, or a prepaid API key (card) |
The deep engine never runs in the locally-installed package β deep=true is forwarded to the hosted /pro/run endpoint, gated by x402 or a prepaid key. The premium engine (the taint/dataflow CFG, the DeFi families, the full detector suite, the calibration corpus) is not shipped in the npm package at all: the files allowlist publishes only the free client, and the deep path is a lazy import() of modules that exist solely on the server. npm pack contains zero premium source β the moat cannot be extracted from the installed package.
Use as an MCP server
{
"mcpServers": {
"solidity-sentinel": {
"command": "npx",
"args": ["-y", "solidity-sentinel-mcp"],
// optional β unlocks the deep audit with a prepaid key:
"env": { "SENTINEL_KEY": "<your-key>" }
}
}
}Tool: audit_contract β { source: string, deep?: boolean }.
deepomitted/false β free verdict (runs locally).deep: truewith aSENTINEL_KEYβ full deep audit (server-side).deep: truewithout a key β you still get the free verdict plus how to unlock the deep tier.
Use as an HTTP API
# Free verdict
curl -s -X POST https://solidity-sentinel.vercel.app/run \
-H 'content-type: application/json' \
-d '{"source":"pragma solidity ^0.8.0; contract C { ... }"}'
# Deep audit β pay per call with x402 (USDC on Base), or a prepaid key:
curl -s -X POST https://solidity-sentinel.vercel.app/pro/run \
-H 'authorization: Bearer <your-key>' \
-H 'content-type: application/json' \
-d '{"source":"..."}'A request to /pro/run without payment returns 402 with both payment lanes (x402 challenge + a Stripe checkout link). Buy a prepaid card key at /pro/checkout.
Develop
npm install
npm run build # tsc + sync landing
npm test # 227 tests: engine + 153-case CVE/hack calibration corpus + taint/CFG/bytecode units + coverage drift-guard
npm run dev:http # local server (FORCE_LISTEN); /run, /pro/run, /mcpLicense
MIT β see LICENSE.
Available Tools
1 toolaudit_contractA
Static security audit of a Solidity smart contract OR a deployed contract's bytecode. Paste the contract source (or raw 0xβ¦ runtime/creation bytecode for an unverified contract) and get a SAFE/REVIEW/HIGH-RISK/CRITICAL verdict with a 0β100 risk score. The FREE tier (no key) runs 4 high-signal detectors (reentrancy, access-control, low-level calls, weak randomness) and returns the verdict + finding counts + top issue titles. Set deep=true for the PREMIUM audit: a real taint/dataflow engine + the full 12-detector suite (incl. flash-loan/oracle manipulation, ERC-4626 inflation, governance/timelock, permit/signature replay) and deployed-bytecode screening β every finding with its exact line, the sourceβsink flow, code evidence, SWC/CWE ids, confidence and a fix. The part an agent can't reproduce in one shot. Call this BEFORE deploying, approving, or sending funds to a contract.
| Name | Required | Description | Default |
|---|---|---|---|
| source | Yes | The full Solidity source code of the contract to audit. | |
| deep | No | When true, runs the PREMIUM full audit. Requires an API key (set SENTINEL_KEY in your MCP env); without one you get the free verdict plus instructions to unlock the deep report. |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden and excels. It details the free and premium audit behaviors, the detectors used, output format (verdict, risk score, findings), and the prerequisite for deep audit (API key). It clearly sets expectations.
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 a single dense paragraph but front-loads the core purpose. Every sentence adds value, though it could be more structured (e.g., bullet points) for quicker scanning. Slightly verbose but still 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 no output schema and two parameters, the description is comprehensive. It covers input types, tiers, output expectations, and use cases. No gaps are evident for an AI agent to understand and invoke the tool correctly.
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 description adds significant meaning beyond the 100% schema coverage. For 'source', it expands to accept bytecode. For 'deep', it explains the premium audit capabilities in detail. This extra context aids correct parameter selection.
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 performs a static security audit of Solidity smart contracts or deployed bytecode, specifying the verb 'audit' and the resource. It effectively distinguishes the tool's function even without sibling 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?
The description provides explicit usage guidance: 'Call this BEFORE deploying, approving, or sending funds to a contract.' It also explains when to use the free vs premium tier, though it does not list alternatives 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.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
1 tool update
v0.1.0- First observed
audit_contract
TDQS
Only one tool exists, so there is no risk of confusion. The tool's purpose is clearly distinct from any other potential tool.
The single tool name follows a clear verb_noun pattern (audit_contract), which is consistent and descriptive. No inconsistencies to evaluate.
With only one tool, the server is on the thin side. However, the tool is comprehensive, encapsulating both free and premium audits via parameters, which somewhat justifies the low count.
The tool covers a wide range of security detectors and audit modes (source code, bytecode, deep analysis). Minor gaps like gas analysis or integration checks are absent but not critical for the core audit purpose.
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Connectors
EVM audit (Slither + source + security.txt + MCP-probe + wallet-exposure). 6 tools + /trace.
AI security scanner for Solidity + free CC0 dataset of Sherlock audit-competition acceptance rates.
Instant rug-check for any EVM or Solana token, distilled to one clear 0-10 risk verdict.
Pre-transaction risk screening for Ethereum addresses: signed score, sanctions, audit trail.
Related MCP Servers
- AlicenseNot gradedqualityBmaintenanceEnables smart contract security auditing using Slither, Aderyn, and custom pattern analysis through the Model Context Protocol, allowing AI assistants to run static analysis and vulnerability checks on Solidity and Vyper contracts.1Apache 2.0
- FlicenseNot gradedqualityCmaintenanceAn MCP server that statically audits Solidity smart contracts for common vulnerabilities like reentrancy and access control, enabling developers to identify and fix security issues via natural language.-
- FlicenseAqualityCmaintenanceFetches verified EVM smart contract source code, scans for vulnerabilities, analyzes token holder distribution, and generates audit reports.5-
- FlicenseAqualityBmaintenanceAudits Ethereum/Solidity smart contracts using the Cysic Minimax model, providing automated vulnerability detection, gas optimization suggestions, and markdown report generation.4-
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
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/Baneado98/solidity-sentinel'
If you have feedback or need assistance with the MCP directory API, please join our Discord server