Ampdat Control MCP server
com.ampdat/controlampdat.comstreamable-httpv1.0.1Scanned
Who controls a DeFi vault (Morpho today), Safe or stablecoin, and what is about to change.
5 tools: 5 only read.
- Reads private data · 1
- Reads text others write · 5
- Can send data out · 0
- No findings
Tools listed without sign-in. Remote posture
With Anlyon
Decide which of this server's tools your agent can use.
- 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 Ampdat Control MCP server can do
The Ampdat Control MCP server is published by ampdat.com, a domain the MCP Registry verified. It has 5 tools. Every one of them only reads: going by their definitions, none of them creates, changes, sends or deletes anything.
1 tool reads private data (get_coverage); 5 tools bring in text other people can write (get_coverage, search_covered_contracts, get_control_state and 2 more).
None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.
Its remote endpoint lists its tools without sign-in.
Last scanned Nov 17, 2026, version 1.0.1.
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
Only reads 5Show 5 read-only tools
get_change_recordsPast and recent changes as records, for monitoring a position or auditing a contract's history: the change history as record/v1 records, oldest first: what changed, from what to wh…Reads text others writeNo findings
Why it is in this group
- The name "get_change_records" says "get": 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 Past and recent changes as records, for monitoring a position or auditing a contract's history: the change history as record/v1 records, oldest first: what changed, from what to what, who acted, who may execute or revoke it, when it takes effect, and the transaction and log each rests on. With `address`, one contract's history; without, the feed across every covered contract (filter with `since`, a block number). Paged: pass the previous result's next_cursor. Paid per call over x402; a call without a payment returns the price and where to buy, and charges nothing.
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
- readOnlyHint: true
- title: Change history and feed (paid)
get_control_evidenceThe machine-readable, evidence-backed answer for one covered contract (the subject/v1 envelope): the full control graph (each Safe's signers, threshold, modules and guard, EIP-7702…Reads text others writeNo findings
Why it is in this group
- The name "get_control_evidence" says "get": 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 The machine-readable, evidence-backed answer for one covered contract (the subject/v1 envelope): the full control graph (each Safe's signers, threshold, modules and guard, EIP-7702 delegates, and what is still unresolved), the complete state (every market, cap and queue), every pending change as a record with the transaction and log it rests on, the 20 most recent changes, and the value at stake. Use it when the user needs to verify or audit, not just read: the whole chain behind a role holder in one answer, what a pending change rests on, or the exact caps. Paid per call over x402; a call without a payment returns the price and where to buy, and charges nothing. get_control_state is the free summary.
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
- readOnlyHint: true
- title: The evidence-backed control answer (paid)
get_control_stateWho controls a covered contract right now: who holds each role and what that holder is (a single key, a Safe and its threshold, a DAO, a known contract); what each role can change …Reads text others writeNo findings
Why it is in this group
- The name "get_control_state" says "get": 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 Who controls a covered contract right now: who holds each role and what that holder is (a single key, a Safe and its threshold, a DAO, a known contract); what each role can change and how much notice (timelock) each change gives; and every change already queued, when it can take effect and who can revoke it. For a Morpho vault, before a deposit or while holding: the owner, curator, guardian or sentinels, and allocators. For a stablecoin: who can mint, burn, pause, freeze, upgrade the contract or appoint those roles. For a Safe: its signers' threshold, modules and guards, and the vault roles it holds (holds_roles_on); a Safe changes in one transaction, so nothing in it is pending. Deterministic facts from the chain at a stated block; a title search, not a rating, so it returns no safety score. An address that is not covered returns covered: false.
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
- readOnlyHint: true
- title: Who controls this contract, and what is pending
get_coverageWhat this server can answer about: which contract families on which chain (today, on Ethereum mainnet: every Morpho vault, MetaMorpho v1.0 and v1.1 and Morpho Vaults V2; the Safes …Reads private dataReads text others writeNo findings
Why it is in this group
- The name "get_coverage" says "get": a word for reading.
What it can reach
- private-dataThe description's first sentence says "vault": it reads secrets.
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it What this server can answer about: which contract families on which chain (today, on Ethereum mainnet: every Morpho vault, MetaMorpho v1.0 and v1.1 and Morpho Vaults V2; the Safes that hold those vaults' roles; and the contracts of six stablecoins, USDC, USDT, USDS, DAI, PYUSD and USD1), how many contracts, and the block the data is at. Call it once to learn the scope, or with `address` to check whether one address is covered before relying on an answer.
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
- readOnlyHint: true
- title: What Ampdat Control covers
search_covered_contractsFind a covered contract's address from words the user gave: its name (e.g.Reads text others writeNo findings
Why it is in this group
- The name "search_covered_contracts" says "search": 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 Find a covered contract's address from words the user gave: its name (e.g. 'Steakhouse USDC'), its asset symbol (e.g. 'WETH') or part of its address. Returns up to `limit` matches with address, name, asset and family. Use it when the user names a vault or a coin instead of giving an address, then call get_control_state with the address.
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
- readOnlyHint: true
- title: Find a covered contract by name
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 outbound.
- Reads private data1
- 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 out0
- 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 18, 2026, 16:18 UTC, unchanged since Nov 18, 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
- 0
- Protocol version
- 2025-06-18
- 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
Findings
Matches of fixed checks, with the text they matched.
No check matched anything in these tool definitions. That is not a safety guarantee.
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 1.0.1. Values in angle brackets are yours to fill in.
claude mcp add --transport http control https://control.ampdat.com/mcpclaude mcp add --transport http control https://control.ampdat.com/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__control__get_coverage",
"mcp__control__search_covered_contracts",
"mcp__control__get_control_state",
"mcp__control__get_control_evidence",
"mcp__control__get_change_records"
],
"ask": [],
"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 control. Review it before you use it.
Capability tags behind 5 rules
- mcp__control__get_coverage private-data, untrusted-input
- mcp__control__search_covered_contracts untrusted-input
- mcp__control__get_control_state untrusted-input
- mcp__control__get_control_evidence untrusted-input
- mcp__control__get_change_records 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/com.ampdat/control/verify?hash=6831b62ca343f18b5bb93267713dddafe964d9be353938a57afa473a72c0a4bc" | jq -e '.changed == false'Pinned hash 6831b62ca343, from Nov 17, 2026, 18:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/com.ampdat/control/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/com.ampdat/control)Source: MCP Registry. Synced Nov 17, 2026, 19:17 UTC.
Ampdat Control MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Ampdat Control MCP server safe?
- No scan can promise that. What its definitions show: 5 tools, all of which only read, and 0 findings from fixed checks. Read-only tools can still pass private data to a model.
Can the Ampdat Control MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the Ampdat Control MCP server do things that cannot be undone?
- No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.
What tools does the Ampdat Control MCP server have?
- 5 tools: 5 read. get_coverage, search_covered_contracts, get_control_state, get_control_evidence and get_change_records.
Does the Ampdat Control MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the Ampdat Control MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the Ampdat Control MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 17, 2026.