Contract Powers
REMOTE · AGENT.ZBANG.NET
Who can still change this EVM contract, and what can they do to holders?
Available components
Last scanned (14 hours ago)
Scores higher than 67% of remote servers
Reachable. Last reached 21 Nov 2026.
Category Crypto and Web3
Recent critical change
TLS certificate (13 Nov 2026). See the changelog before you install this server.
How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →
Endpoint Security57
- The endpoint's TLS certificate is valid, in date, and uses a strong key. View diagnostics → Pass
- Authorisation not fully verified: no authorisation is required to call this server, and 4 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe. See how to fix → View diagnostics → Unverified
- HTTPS is enforced; there's no plaintext access path. View diagnostics → Pass
- HSTS check failed: the Strict-Transport-Security header is absent. See how to fix → View diagnostics → Fail
- DNSSEC check failed: this domain isn't protected by DNSSEC. See how to fix → View diagnostics → Fail
Transport & Reachability100
- Verified streamable-http transport via a live MCP handshake. View diagnostics → Pass
Schema Quality & AI Usability70
- AI-judged instruction clarity (excellent).Pass
- Context-footprint check failed: tool/resource definitions use about 692 tokens (~173/item across 4 items; 4 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management100
- No destabilizing schema changes in the last 30 days.Pass
Tool Coverage100
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 100% of tool parameters carry a description.Pass
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 4 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 5 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a current MCP spec version (2026-07-28).Pass
Checks we ran (12)
- TLS certificate
- HTTPS
- HSTS header
- DNSSEC
- Transport
- Schema quality
- Stability
- Tool coverage
- Injection markers
- Destructive annotations
- Judged manipulation
- MCP protocol
Checks we could not complete (1)
These are gaps on our side, not findings about this hosted endpoint. We only credit what we can confirm, so a category made up entirely of them scores 0.
- Authorization in Endpoint SecurityAuthorisation not fully verified: no authorisation is required to call this server, and 4 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe.
Does not apply to this hosted endpoint (2)
- Supply Chain SecurityScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.
- Provenance & TransparencyScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.
The score does not measure everything. What the score does not measure →
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 16 Nov 26 0
- Stability: 0.97 → pass security
- 15 Nov 26 0
- HSTS header: unverified → fail ▼ security
- HTTPS: unverified → pass ▲ security
- Injection markers: unverified → pass ▲ security
- TLS certificate: fail → pass ▲ security
- Transport: fail → pass ▲ security
- Authorization: Authorisation not fully verified: no authorisation is required to call this server, and 4 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe. security
- Endpoint reachability: unreachable → reachable ▲ functional
- Tool coverage: unverified → 100 ▲ functional
- MCP protocol: unverified → pass ▲ functional
- Stability: unverified → 0.97 ▲ functional
- Score status: failed → scored ▲ functional
- 13 Nov 26 0
- TLS certificate: pass → fail ▼ critical
- Score status: scored → failed ▼ critical
- Endpoint reachability: reachable → unreachable ▼ security
- HSTS header: fail → unverified ▼ security
- Stability: pass → unverified ▼ security
- Tool safety: pass → unverified ▼ security
- HTTPS: pass → unverified ▼ security
- Transport: pass → fail ▼ security
- Authorization: Authorisation not yet verified: we couldn't confirm whether this endpoint requires it. security
- Capabilities: pass → unverified ▼ functional
- Tool coverage: 100 → unverified ▼ functional
- 11 Nov 26 0
- Stability: 0.97 → pass security
- 10 Nov 26 0
- Stability: pass → 0.97 functional
- 8 Nov 26 0
- Stability: 0.97 → pass security
- 7 Nov 26 0
- Stability: pass → 0.97 functional
- 6 Nov 26 0
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 21 Nov 2026 · Probed https://agent.zbang.net/api/mcp
TLS valid
Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .
| Subject | Issuer | Valid from | Valid until | Key | Signature | Serial |
|---|---|---|---|---|---|---|
| CN=agent.zbang.net | CN=YE1,O=Let's Encrypt,C=US | 23 Oct 2026 | 21 Jan 2027 | ECDSA 256 | ECDSA-SHA384 | 691fbb063c55cad4e79a136050f763f8725 |
| SANs: agent.zbang.net | ||||||
| CN=YE1,O=Let's Encrypt,C=US (CA) | CN=Root YE,O=ISRG,C=US | 3 Sept 2025 | 2 Sept 2028 | ECDSA 384 | ECDSA-SHA384 | 5ddd70dd31f801c85c186a7a04b80afe |
| CN=Root YE,O=ISRG,C=US (CA) | CN=ISRG Root X2,O=Internet Security Research Group,C=US | 13 May 2026 | 2 Sept 2032 | ECDSA 384 | ECDSA-SHA384 | 872165fc34b6e5fba8add5b3705fb53a |
| CN=ISRG Root X2,O=Internet Security Research Group,C=US (CA) | CN=ISRG Root X1,O=Internet Security Research Group,C=US | 13 May 2026 | 2 Sept 2032 | ECDSA 384 | SHA256-RSA | 6c8f1dc727c7117f7baf853ac980f9cd |
Background: What to check on a remote MCP endpoint →
DNSSEC insecure
Validation of agent.zbang.net. — Not signed
| Zone | DS | Keys | Algorithms | Outcome |
|---|---|---|---|---|
| . | Trust anchor | 20326, 38696 | 8, 8 | Verified |
| net. | DS published | 37331 | 13 | Verified |
| zbang.net. | No DS | Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation |
Authentication No authorisation required
The endpoint answered without asking for a token. Anyone who knows the URL can reach it.
| Result | No authorisation required |
|---|---|
| HTTP status | 200 |
Background: How OAuth 2.1 works in the 2026 MCP spec →
Transports 2 probes
| Transport | URL | Outcome | Status | Location |
|---|---|---|---|---|
| streamable-http | https://agent.zbang.net/api/mcp | Verified | 200 | |
| http (plaintext) | http://agent.zbang.net/api/mcp | HTTPS enforced | 301 | https://agent.zbang.net/api/mcp |
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
check_any_contract ~138
Free preview for ANY verified EVM contract on base, ethereum or polygon — including addresses not in the registry. Returns contract type, verification, name, whether it is a proxy, how many powers were found, how many owner-only functions went uncategorised, and whether an owner was found. The decision fields (which powers, the evidence, the admin address, the implementation) are withheld and listed by name. Use get_contract_powers first if the contract is already in the registry — that is free and complete.
| Name | Type | Req | Description |
|---|---|---|---|
| address | string | yes | 0x-prefixed 20-byte address. |
| chain | string | – | Default base. |
No output schema declared.
No examples provided.
get_contract_powers ~163
Full free analysis of one contract that is in the registry: verification, proxy pattern and implementation address, who the admin is and whether it is a single key, every retained power (upgrade / mint / grant-minter / pause / blacklist / seize / fees / sweep / burn-from / ownership transfer / limits) with the evidence and confidence behind it, reachable DELEGATECALL / SELFDESTRUCT / CREATE2 opcodes, and the owner-only functions the classifier could NOT categorise — which is where the unusual powers hide. Accepts an address or a symbol such as USDC or AERO.
| Name | Type | Req | Description |
|---|---|---|---|
| chain | string | – | Required if a symbol is ambiguous. |
| contract | string | yes | A 0x address, or a symbol such as USDC. |
No output schema declared.
No examples provided.
list_watched_contracts ~162
List the EVM contracts in the Contract Powers registry, with a one-line risk shape for each: is the code upgradeable, is the admin a single key (EOA) rather than a contract, how many powers are declared, and is it covered by a bug bounty. Use this to see what is already analysed before spending a lookup. Filters are optional and combine with AND.
| Name | Type | Req | Description |
|---|---|---|---|
| chain | string | – | Restrict to one chain. |
| limit | integer | – | Default 200. |
| single_key_admin | boolean | – | true = only contracts whose admin is a plain wallet (EOA), not a contract/multisig/timelock. |
| upgradeable | boolean | – | true = only contracts whose code can still be replaced. |
No output schema declared.
No examples provided.
recent_power_changes ~106
What actually changed behind the watched contracts: implementation swapped, owner moved, a power appeared or disappeared, verification lost. Each event carries the before and after value and the window it was detected in. Severity is one of critical / material / low. Use this to answer "has anything changed behind this contract recently?".
| Name | Type | Req | Description |
|---|---|---|---|
| contract | string | – | Filter to one address or symbol. |
| limit | integer | – | Default 25. |
| severity | string | – | Minimum severity to return. |
No output schema declared.
No examples provided.
How do I install the Contract Powers MCP server?
Contract Powers is a hosted endpoint at https://agent.zbang.net/api/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
remote · agent.zbang.net
claude mcp add --transport http ofirbaranesad-agent-contract-powers 'https://agent.zbang.net/api/mcp'
What is the Contract Powers MCP server?
Contract Powers is an MCP server listed in the public MCP registry as io.github.ofirbaranesad-agent/contract-powers. Who can still change this EVM contract, and what can they do to holders? This page covers its hosted endpoint (https://agent.zbang.net/api/mcp).
Is the Contract Powers MCP server safe to use?
Contract Powers scores 77 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the Contract Powers MCP server expose?
Contract Powers exposes 4 tools: list_watched_contracts, get_contract_powers, check_any_contract, recent_power_changes. Their descriptions and schemas cost roughly 569 tokens of context every time the server is loaded.
Does the Contract Powers MCP server require authentication?
No. We connected to Contract Powers without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.
Is the Contract Powers MCP server still maintained?
Contract Powers is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.
What did VerifyMCP test on the Contract Powers MCP server?
VerifyMCP ran 12 checks on Contract Powers, covering TLS certificate, HTTPS, HSTS header, DNSSEC and 8 more. One item could not be completed, a gap on our side rather than a finding about Contract Powers: Authorization. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.