DLL Execution MCP server
io.github.dllio/dll-executiondlliostreamable-httpv0.1.0Scanned
Free read-only Base Mainnet transaction Preflight and Verification; no signing or custody.
2 tools: 2 do something that can't be undone.
- Reads private data · 0
- Reads text others write · 2
- Can send data out · 1
- 2 findings
Sign-in required, no OAuth metadata. Remote posture
Anlyon alternative
2 of these tools change something. Run those as governed actions.
Declare what an action changes, and Anlyon puts it under a shared limit, binds every approval to the exact request, and grades the outcome. It works on any HTTPS API you can describe as an action.
Anlyon Radar does not run, proxy or govern this MCP server. A tool your own code calls directly is not routed through Anlyon and is not governed by it.
Import an OpenAPI spec →What the DLL Execution MCP server can do
The DLL Execution MCP server is published by the GitHub account dllio. It has 2 tools. It can do things that cannot be undone, such as sending, paying or publishing (preflight_transaction and verify_transaction), but cannot delete data. None of its tools only reads.
2 tools bring in text other people can write (preflight_transaction and verify_transaction); 1 tool can send data out of your system (preflight_transaction).
The fixed checks matched 2 findings (annotation-conflict). Each one comes with the text it matched.
Last scanned Nov 5, 2026, version 0.1.0.
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.
2 tools
Can't be undone 2Claude Code: ask
preflight_transactionBefore signing: simulate one unsigned Base Mainnet (8453) candidate (chain_id/from/to/value/data); inspect call success/revert, top-level destination and L2 fee constraints, Judgme…Reads text others writeCan send data out1 finding
Why it is in this group
- The input addresses people (input.candidate.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.candidate.to): what the tool writes goes there.
Findings
- Warn
The server marks "preflight_transaction" 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":false,"openWorldHint":true}; The input addresses people (input.candidate.to): what it sends cannot be taken back.
Description, as the server wrote it Before signing: simulate one unsigned Base Mainnet (8453) candidate (chain_id/from/to/value/data); inspect call success/revert, top-level destination and L2 fee constraints, Judgment, reason codes and evidence. Free; no API key, wallet or payment. Complete supported EIP-1559 fee_estimation context optionally estimates L1/L2/applicable Operator/Total Network Fee separately; legacy Judgment is unchanged, not automatic PASS. Inspect http_status, response.judgment and response.simulation. After broadcast use verify_transaction. No signing, broadcasting, custody, asset-delta/risk scan or execution guarantee.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
verify_transactionAfter independent broadcast: verify a Base Mainnet (8453) transaction against explicit inclusion, receipt-status and optional candidate-field expectations.Reads text others write1 finding
Why it is in this group
- The input addresses people (input.expectation.candidate.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.
Findings
- Warn
The server marks "verify_transaction" 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":false,"openWorldHint":true}; The input addresses people (input.expectation.candidate.to): what it sends cannot be taken back.
Description, as the server wrote it After independent broadcast: verify a Base Mainnet (8453) transaction against explicit inclusion, receipt-status and optional candidate-field expectations. transaction_hash is required; default checks inclusion, NOT receipt success. Free; no API key, wallet or payment. Read http_status, response.verification.state and response.observation_errors; missing evidence is not success. Before signing use preflight_transaction. VERIFIED is not finality, ownership, causality, asset-balance change verification or a swap economic-outcome guarantee. No signing, broadcasting or custody.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
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 write2
- 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 20, 2026, 19:04 UTC, unchanged since Nov 20, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 525
- tools/list served without credentials
- no
- Tools that change things, listed without credentials
- 0
- Protocol version
- not observed
- 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
The probe stopped: initialize answered HTTP 525.
Posture changes
- Nov 20, 2026
- Reachable: no to yes
- HTTP status of an anonymous initialize: none to 525
- Nov 13, 2026
- Reachable: yes to no
- HTTP status of an anonymous initialize: 200 to none
- tools/list served without credentials: yes to no
- Tools that change things, listed without credentials: 2 to 0
- Protocol version: 2025-06-18 to none
Findings
Matches of fixed checks, with the text they matched.
The server marks "preflight_transaction" 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":false,"openWorldHint":true}; The input addresses people (input.candidate.to): what it sends cannot be taken back.
The server marks "verify_transaction" 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":false,"openWorldHint":true}; The input addresses people (input.expectation.candidate.to): what it sends cannot be taken back.
History
Changes to its tool definitions and to its remote endpoint, newest first.
PostureRemote posture changed. Reachable: no -> yes; HTTP status of an anonymous initialize: none -> 525.View diff
- Reachable: no to yes
- HTTP status of an anonymous initialize: none to 525
PostureRemote posture changed. Reachable: yes -> no; HTTP status of an anonymous initialize: 200 -> none; tools/list served without credentials: yes -> no (and 2 more).View diff
- Reachable: yes to no
- HTTP status of an anonymous initialize: 200 to none
- tools/list served without credentials: yes to no
- Tools that change things, listed without credentials: 2 to 0
- Protocol version: 2025-06-18 to none
Install
Pinned to version 0.1.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http dll-execution https://execution.dll.io/mcpclaude mcp add --transport http dll-execution https://execution.dll.io/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": [],
"ask": [
"mcp__dll-execution__preflight_transaction",
"mcp__dll-execution__verify_transaction"
],
"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 dll-execution. Review it before you use it.
Capability tags behind 2 rules
- mcp__dll-execution__preflight_transaction untrusted-input, outbound
- mcp__dll-execution__verify_transaction 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/io.github.dllio/dll-execution/verify?hash=ae0a8b42bdd3a69c26c4557779d14abedea92ebc404b2b8516274137a10d8cf5" | jq -e '.changed == false'Pinned hash ae0a8b42bdd3, from Nov 5, 2026, 17:17 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/io.github.dllio/dll-execution/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/io.github.dllio/dll-execution)Source: MCP Registry · repository. Synced Oct 21, 2026, 18:32 UTC.
DLL Execution MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the DLL Execution MCP server safe?
- No scan can promise that. What its definitions show: 2 tools, 2 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 DLL Execution MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the DLL Execution MCP server do things that cannot be undone?
- Yes. 2 tools can send, pay, publish or merge: preflight_transaction and verify_transaction.
What tools does the DLL Execution MCP server have?
- 2 tools: 2 irreversible. preflight_transaction and verify_transaction.
Does the DLL Execution MCP server need sign-in or OAuth?
- Its remote endpoint did not answer the last anonymous look.
Does the DLL Execution 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): preflight_transaction.
Has the DLL Execution MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 5, 2026.