ERC-7715 Session-Key, Smart-Account & AI Agent Spend Cap MCP server
dev.workers.b2bintel-edge.agent-spend-guard/erc-7715-session-key-smart-account-spend-mcpagent-spend-guard.b2bintel-edge.workers.devstreamable-httpv2.4.0Scanned
Build ERC-7715 & Coinbase Smart Wallet bounded daily spend permissions and session-key guards.
5 tools: 1 do something that can't be undone, 3 change things and 1 only read.
- Reads private data · 0
- Reads text others write · 5
- Can send data out · 1
- 2 findings
Tools listed without sign-in. Remote posture
With Anlyon
1 tool here does something that can't be undone. Govern it.
- Anlyon lists the tools and adopts none.
- Each tool you adopt gets approvals and receipts.
- Your agent never holds the key.
A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.
What the ERC-7715 Session-Key, Smart-Account & AI Agent Spend Cap MCP server can do
The ERC-7715 Session-Key, Smart-Account & AI Agent Spend Cap MCP server is published by agent-spend-guard.b2bintel-edge.workers.dev, a domain the MCP Registry verified. It has 5 tools. It can do things that cannot be undone, such as sending, paying or publishing (simulate_evm_tx_and_spend_firewall) and create or change data (3 tools: build_erc7715_and_coinbase_spend_permission, audit_token_contract_technical_risks and verify_package_anti_hallucination), but cannot delete data. 1 tool only reads.
5 tools bring in text other people can write (build_erc7715_and_coinbase_spend_permission, simulate_evm_tx_and_spend_firewall, audit_token_contract_technical_risks and 2 more); 1 tool can send data out of your system (simulate_evm_tx_and_spend_firewall).
The fixed checks matched 2 findings (annotation-conflict). Each one comes with the text it matched.
Its remote endpoint lists its tools without sign-in.
Last scanned Nov 21, 2026, version 2.4.0.
Tools
Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.
5 tools
Can't be undone 1Claude Code: ask
simulate_evm_tx_and_spend_firewallSimulates any unsigned EVM transaction via eth_call + eth_estimateGas, detects dangerous unlimited ERC-20 approvals, and verifies total USD outflow against the agent's budget cap.Reads text others writeCan send data out1 finding
Why it is in this group
- The input addresses people (input.to): what it sends cannot be taken back.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe input takes a destination (input.to): what the tool writes goes there.
Findings
- Warn
The server marks "simulate_evm_tx_and_spend_firewall" read-only (readOnlyHint: true), and its own name, description or input give the class "irreversible".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The input addresses people (input.to): what it sends cannot be taken back.
Description, as the server wrote it Simulates any unsigned EVM transaction via eth_call + eth_estimateGas, detects dangerous unlimited ERC-20 approvals, and verifies total USD outflow against the agent's budget cap.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
- title: Pre-Flight Simulate EVM Transaction for Reverts, Gas & Spend Cap
Changes things 3Claude Code: ask
audit_token_contract_technical_risksChecks GoPlus and DexScreener telemetry for honeypot traps, buy/sell tax %, hidden owner privileges, and live pool liquidity before swapping.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Checks GoPlus and DexScreener telemetry for honeypot traps, buy/sell tax %, hidden owner privileges, and live pool liquidity before swapping.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
- title: Audit ERC-20 Token Bytecode for Honeypot, Tax & Liquidity Risks
build_erc7715_and_coinbase_spend_permissionGenerates non-custodial ERC-7715 wallet_grantPermissions JSON-RPC and Coinbase SpendPermissionManager EIP-712 structs to bound AI agent daily/per-tx USDC spending.Reads text others write1 finding
Why it is in this group
- The description's first verb is "generate": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Findings
- Warn
The server marks "build_erc7715_and_coinbase_spend_permission" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The description's first verb is "generate": a word for a change.
Description, as the server wrote it Generates non-custodial ERC-7715 wallet_grantPermissions JSON-RPC and Coinbase SpendPermissionManager EIP-712 structs to bound AI agent daily/per-tx USDC spending.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
- title: Build ERC-7715 Session Key & Coinbase SpendPermission Payloads
verify_package_anti_hallucinationChecks live npm and PyPI registries to block nonexistent hallucinated package names and flag newly registered slopsquatting traps (<14 days old).Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Checks live npm and PyPI registries to block nonexistent hallucinated package names and flag newly registered slopsquatting traps (<14 days old).
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
- title: Verify npm or PyPI Package Against AI Hallucination & Slopsquatting
Only reads 1Show 1 read-only tool
plan_and_build_guarded_rebalance_swapReads live ETH + USDC wallet balances, enforces maxSpendCapUsd, and assembles ready-to-sign non-custodial multi-DEX swap calldata saving 71% vs standard wallet swap fees.Reads text others writeNo findings
Why it is in this group
- The description's first verb is "read": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Reads live ETH + USDC wallet balances, enforces maxSpendCapUsd, and assembles ready-to-sign non-custodial multi-DEX swap calldata saving 71% vs standard wallet swap fees.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
- title: Plan Portfolio Drift & Build Spend-Capped 0.25% Multi-DEX Swap Calldata
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Exfil surface
Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.
No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data.
- Reads private data0
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write5
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out1
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.
Remote posture
What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.
Looked at Nov 21, 2026, 19:19 UTC, unchanged since Nov 21, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 200
- tools/list served without credentials
- yes
- Tools that change things, listed without credentials
- 8
- Protocol version
- 2025-03-26
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- not observed
- Authorization servers
- not observed
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- not observed
- Client ID metadata documents
- not observed
- HighThe whole server
The endpoint served tools/list without credentials, and the list has 8 tools that change things (1 irreversible, 7 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://agent-spend-guard.b2bintel-edge.workers.dev/mcp: tools/list returned 10 tools to an anonymous client, including simulate_evm_tx_and_spend_firewall (irreversible), build_erc7715_and_coinbase_spend_permission (write), audit_token_contract_technical_risks (write), verify_package_anti_hallucination (write), safe_snipe_swap_with_honeypot_firewall (write) and 3 more
Findings
Matches of fixed checks, with the text they matched.
The server marks "build_erc7715_and_coinbase_spend_permission" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The description's first verb is "generate": a word for a change.
The server marks "simulate_evm_tx_and_spend_firewall" read-only (readOnlyHint: true), and its own name, description or input give the class "irreversible".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The input addresses people (input.to): what it sends cannot be taken back.
History
Changes to its tool definitions and to its remote endpoint, newest first.
No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.
Install
Pinned to version 2.4.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http erc-7715-session-key-smart-account-spend https://agent-spend-guard.b2bintel-edge.workers.dev/mcpclaude mcp add --transport http erc-7715-session-key-smart-account-spend https://agent-spend-guard.b2bintel-edge.workers.dev/mcpRun in a terminal.
Claude Code permissions
Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [
"mcp__erc-7715-session-key-smart-account-spend__plan_and_build_guarded_rebalance_swap"
],
"ask": [
"mcp__erc-7715-session-key-smart-account-spend__build_erc7715_and_coinbase_spend_permission",
"mcp__erc-7715-session-key-smart-account-spend__simulate_evm_tx_and_spend_firewall",
"mcp__erc-7715-session-key-smart-account-spend__audit_token_contract_technical_risks",
"mcp__erc-7715-session-key-smart-account-spend__verify_package_anti_hallucination"
],
"deny": []
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as erc-7715-session-key-smart-account-spend. Review it before you use it.
Capability tags behind 5 rules
- mcp__erc-7715-session-key-smart-account-spend__build_erc7715_and_coinbase_spend_permission untrusted-input
- mcp__erc-7715-session-key-smart-account-spend__simulate_evm_tx_and_spend_firewall untrusted-input, outbound
- mcp__erc-7715-session-key-smart-account-spend__audit_token_contract_technical_risks untrusted-input
- mcp__erc-7715-session-key-smart-account-spend__verify_package_anti_hallucination untrusted-input
- mcp__erc-7715-session-key-smart-account-spend__plan_and_build_guarded_rebalance_swap untrusted-input
Pin
Keep the decision: fail CI when the tools change, follow every change, or show a badge.
Pin in CI
Fail a build when the tools you reviewed are not the tools the server serves today.
curl -s "https://radar.anlyon.com/api/v1/servers/dev.workers.b2bintel-edge.agent-spend-guard/erc-7715-session-key-smart-account-spend-mcp/verify?hash=29e68290e3a11b2d395b7f532cc080b3934d1660b7dfb881209b071f37d6fda7" | jq -e '.changed == false'Pinned hash 29e68290e3a1, from Nov 21, 2026, 03:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/dev.workers.b2bintel-edge.agent-spend-guard/erc-7715-session-key-smart-account-spend-mcp/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/dev.workers.b2bintel-edge.agent-spend-guard/erc-7715-session-key-smart-account-spend-mcp)Source: MCP Registry · repository. Synced Nov 21, 2026, 03:17 UTC.
ERC-7715 Session-Key, Smart-Account & AI Agent Spend Cap MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the ERC-7715 Session-Key, Smart-Account & AI Agent Spend Cap MCP server safe?
- No scan can promise that. What its definitions show: 5 tools, 4 of which can change, send or delete something, and 2 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the ERC-7715 Session-Key, Smart-Account & AI Agent Spend Cap MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the ERC-7715 Session-Key, Smart-Account & AI Agent Spend Cap MCP server do things that cannot be undone?
- Yes. 1 tool can send, pay, publish or merge: simulate_evm_tx_and_spend_firewall.
What tools does the ERC-7715 Session-Key, Smart-Account & AI Agent Spend Cap MCP server have?
- 5 tools: 1 irreversible, 3 write, 1 read. simulate_evm_tx_and_spend_firewall, build_erc7715_and_coinbase_spend_permission, audit_token_contract_technical_risks, verify_package_anti_hallucination and plan_and_build_guarded_rebalance_swap.
Does the ERC-7715 Session-Key, Smart-Account & AI Agent Spend Cap MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the ERC-7715 Session-Key, Smart-Account & AI Agent Spend Cap MCP server send data to outside services?
- 1 tool can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): simulate_evm_tx_and_spend_firewall.
Has the ERC-7715 Session-Key, Smart-Account & AI Agent Spend Cap MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 21, 2026.