Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

ASMHunter

PYPI · ASMHUNTER-MCP · SCANNED SEP 20

Drive ASMHunter attack-surface monitoring from an AI agent: recon, scans, findings, reports.

Available components

0 this week 58 Trust /100
Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →

Supply Chain Security100
  • No malware found by supply-chain analysis.Pass
  • No known CVEs affecting this package version or its production dependencies.Pass
  • Runs hatchling.build at install time, a recognised native-build step with no shell scripting around it. View diagnostics → Pass
  • 1 of 23 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency6
Schema Quality & AI Usability72
  • AI-judged instruction clarity (good).Pass
  • Tool/resource definitions use about 1771 tokens (~52/item across 34 items; 34 tools + 0 resources), lean.Pass
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management0
  • Stability not yet verified: two runs of the same published version returned different tool surfaces, so we cannot tell a change in the package from a difference in our own sandbox run.Unverified
Tool Coverage71
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 0% of tool parameters carry a description.Fail
  • Structured output schemas are declared (91% of tools); any adoption earns full credit.Pass
Tool Safety75
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • 0 of 3 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "delete_session" implies "delete" and declares no destructiveHint at all, which the MCP spec reads as destructive by default. See how to fix → Fail
  • An AI judge read all 34 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

Unverified: 1 category

A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.

Install

How do I install the ASMHunter MCP server?

ASMHunter runs locally as a PyPI package, launched with uvx asmhunter-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

pypi · asmhunter-mcp

# add to Claude Code
claude mcp add app-asmhunter-asmhunter-mcp -- uvx asmhunter-mcp
// .cursor/mcp.json
{
  "mcpServers": {
    "app-asmhunter-asmhunter-mcp": {
      "command": "uvx",
      "args": [
        "asmhunter-mcp"
      ]
    }
  }
}
// .vscode/mcp.json
{
  "servers": {
    "app-asmhunter-asmhunter-mcp": {
      "command": "uvx",
      "args": [
        "asmhunter-mcp"
      ]
    }
  }
}
# add to Codex CLI
codex mcp add app-asmhunter-asmhunter-mcp -- uvx asmhunter-mcp
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "app-asmhunter-asmhunter-mcp": {
      "type": "local",
      "command": [
        "uvx",
        "asmhunter-mcp"
      ],
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add app-asmhunter-asmhunter-mcp --command uvx --arg asmhunter-mcp
# ~/.hermes/config.yaml
mcp_servers:
  app-asmhunter-asmhunter-mcp:
    command: "uvx"
    args: ["asmhunter-mcp"]
// ~/.netclaw/config/netclaw.json
{
  "McpServers": {
    "app-asmhunter-asmhunter-mcp": {
      "Transport": "stdio",
      "Command": "uvx",
      "Arguments": [
        "asmhunter-mcp"
      ]
    }
  }
}
# add to Vellum
assistant mcp add app-asmhunter-asmhunter-mcp -t stdio -c uvx -a asmhunter-mcp
// mcp.json
{
  "mcpServers": {
    "app-asmhunter-asmhunter-mcp": {
      "command": "uvx",
      "args": [
        "asmhunter-mcp"
      ]
    }
  }
}
Changelog

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.

  • 9 Sept 26 −13
    • Stability: 0.93 → unverified security
    • Tool coverage: 100% → 91% functional
  • 6 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 83 to 87. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 26 at this one. The score rises as the window fills, whether or not the server changes.

  • 4 Sept 26 −2
    • Stability: pass → 0.80 functional
  • 3 Sept 26 +15
    • Malware scan: unverified → pass security
    • Stability: 0.97 → pass security
  • 2 Sept 26 −14
    • Malware scan: pass → unverified security
    • MCP protocol: Implements a current MCP spec version (2026-07-28). functional
  • 30 Aug 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 83 to 87. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 26 at this one. The score rises as the window fills, whether or not the server changes.

  • 28 Aug 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 77 to 80. That category is still filling its 30-day observation window: 23 days of observed history at the previous scan, 24 at this one. The score rises as the window fills, whether or not the server changes.

  • 26 Aug 26 +1
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
Diagnostics

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 20 Sept 2026 · Analysed pypi/asmhunter-mcp@0.1.2

Provenance No attestation

The registry publishes no build provenance for this version, so there is nothing to verify.

Result No attestation
Ecosystem pypi

Background: How many MCP packages publish verified provenance →

Install scripts 1 script
Hook Tier Command
build_backend allowlisted hatchling.build

Background: Why install scripts are a supply-chain risk →

Dependencies 23 packages
Packages resolved 23
Stale 1
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 34 exposed · ~1,771 tokens

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 →

Tool Tokens
add_finding ~112

Log a confirmed finding (promote to a report later). method/url = request context; tags = labels; chain_id = link entries into one exploit chain; retest_at = ISO time to revisit.

NameTypeReqDescription
bodystring
chain_id
method
retest_at
session_idstringyes
severity
tags
target_id
titlestringyes
url

Structured output declared, but exposes no named fields.

No examples provided.

add_lead ~92

Log a lead (a promising-but-unconfirmed angle). method/tags/chain_id/retest_at supported.

NameTypeReqDescription
bodystring
chain_id
method
retest_at
session_idstringyes
severity
tags
target_id
titlestringyes
url

Structured output declared, but exposes no named fields.

No examples provided.

add_note ~94

Add a working note (recon synthesis, blockers, resume info). method/tags/chain_id/retest_at supported.

NameTypeReqDescription
bodystring
chain_id
method
retest_at
session_idstringyes
severity
tags
target_id
titlestringyes
url

Structured output declared, but exposes no named fields.

No examples provided.

add_tested ~94

Record a tested-and-clear surface so you don't retest it. method/tags/chain_id/retest_at supported.

NameTypeReqDescription
bodystring
chain_id
method
retest_at
session_idstringyes
severity
tags
target_id
titlestringyes
url

Structured output declared, but exposes no named fields.

No examples provided.

add_win ~88

Log a bounty win. Pass vulnerability_id/report_id/target_id to link it (sets surfaced_by_asmhunter when a product finding is referenced).

NameTypeReqDescription
amount_usd
notestring
platform
report_id
severity
target_id
titlestringyes
vulnerability_id

Structured output declared, but exposes no named fields.

No examples provided.

bulk_add_entries ~46

Add many entries at once. Each: {type,title,body?,severity?,target_id?,url?}.

NameTypeReqDescription
entriesarrayyes
session_idstringyes

No output schema declared.

No examples provided.

create_session ~95

Start a hunt session (program-anchored or freeform). Auto-links the program's targets. Pass `goal` to state the objective for this session (e.g. "find IDOR in the billing API"). It is stored and returned by get_session, so you can keep the session focused on it.

NameTypeReqDescription
goal
program_id
target_ids
titlestringyes

Structured output declared, but exposes no named fields.

No examples provided.

create_target ~33

Add a scan target (optionally linked to a program).

NameTypeReqDescription
domainstringyes
program_id

Structured output declared, but exposes no named fields.

No examples provided.

delete_entry ~20

Delete an entry.

NameTypeReqDescription
entry_idstringyes

Structured output declared, but exposes no named fields.

No examples provided.

delete_report ~21

Delete a report draft.

NameTypeReqDescription
report_idstringyes

Structured output declared, but exposes no named fields.

No examples provided.

delete_session ~23

Delete a session and its entries.

NameTypeReqDescription
session_idstringyes

Structured output declared, but exposes no named fields.

No examples provided.

draft_report ~89

Create a report draft (vuln_class one of: xss,idor,ssrf,sqli,ssti,xxe,csrf,oauth,default_credentials,info_disclosure,rce,open_redirect).

NameTypeReqDescription
request_raw
response_raw
steps
target_id
titlestringyes
vuln_classstringyes

Structured output declared, but exposes no named fields.

No examples provided.

get_findings ~35

Your vulnerability findings (filter by severity/search).

NameTypeReqDescription
limitinteger
search
severity

Structured output declared, but exposes no named fields.

No examples provided.

get_my_stats ~22

Your hunt stats: sessions, entry breakdown, per-program activity.

Input schema present but exposes no named parameters.

Structured output declared, but exposes no named fields.

No examples provided.

get_program ~185

Full program detail + scope. `program` is a program_id (UUID) OR a handle (e.g. 'shopify'). Pass `platform` to disambiguate a handle shared across platforms. (Find ids/handles via search_programs / recommend_programs.) The returned `assets` list contains BOTH in-scope and out-of-scope scope items (in-scope first); each asset carries an `in_scope` boolean — `in_scope: false` means the asset is explicitly OUT OF SCOPE (do not test or submit against it). Set `include_out_of_scope=False` for an in-scope-only list. Without this the API returns in-scope assets only, hiding the out-of-scope set entirely.

NameTypeReqDescription
include_out_of_scopeboolean
platform
programstringyes

Structured output declared, but exposes no named fields.

No examples provided.

get_scan_status ~23

Status of a scan run.

NameTypeReqDescription
scan_idstringyes

Structured output declared, but exposes no named fields.

No examples provided.

get_scope_changes ~37

Recent scope additions/removals across tracked programs.

NameTypeReqDescription
change_type
limitinteger
platform

Structured output declared, but exposes no named fields.

No examples provided.

get_session ~26

A session with all its entries + linked targets.

NameTypeReqDescription
session_idstringyes

Structured output declared, but exposes no named fields.

No examples provided.

get_value_receipt ~39

What ASMHunter surfaced for you (30d) + your logged-win totals. Use this to ground recommendations in the user's actual monitored surface.

Input schema present but exposes no named parameters.

Structured output declared, but exposes no named fields.

No examples provided.

get_watchlist ~42

Your watched programs with full metrics (bounties, dupe, health, scope) + prior_sessions per program. Use to resume hunting on programs you track.

Input schema present but exposes no named parameters.

Structured output declared, but exposes no named fields.

No examples provided.

list_assets ~37

Discovered assets/hosts (filter by target/search).

NameTypeReqDescription
limitinteger
search
target_id

Structured output declared, but exposes no named fields.

No examples provided.

list_entries ~32

List a session's entries (optionally one type).

NameTypeReqDescription
session_idstringyes
type

No output schema declared.

No examples provided.

list_reports ~26

List your report drafts/submissions.

NameTypeReqDescription
status
target_id

Structured output declared, but exposes no named fields.

No examples provided.

list_sessions ~26

List your hunt sessions (filter by active/paused/completed).

NameTypeReqDescription
status

Structured output declared, but exposes no named fields.

No examples provided.

list_targets ~12

Your scan targets.

Input schema present but exposes no named parameters.

Structured output declared, but exposes no named fields.

No examples provided.

list_wins ~22

List the user's logged bounty wins (private, self-reported).

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

list_workflows ~55

Available scan workflows: each item has workflow_id + display_name + description + tier lock. Call this BEFORE trigger_scan to choose a valid workflow_id (e.g. recon, subdomain enumeration, vuln scan, JS secrets).

Input schema present but exposes no named parameters.

Structured output declared, but exposes no named fields.

No examples provided.

promote_entry ~30

Promote a finding entry into a report draft. Returns {report_id}.

NameTypeReqDescription
entry_idstringyes

Structured output declared, but exposes no named fields.

No examples provided.

recommend_programs ~45

Ranked program recommendations with reasons (opportunity, dupe, health, prior sessions).

NameTypeReqDescription
limitinteger
min_bounty
platform

Structured output declared, but exposes no named fields.

No examples provided.

search_programs ~31

Search bug-bounty programs by name.

NameTypeReqDescription
limitinteger
querystringyes

Structured output declared, but exposes no named fields.

No examples provided.

trigger_scan ~60

Queue a real scan (pro+, consumes scan quota). Re-call with confirm=true to actually run it.

NameTypeReqDescription
confirmboolean
target_domainstringyes
target_idstringyes
workflow_idstringyes

Structured output declared, but exposes no named fields.

No examples provided.

update_entry ~91

Update an entry (close a lead, set severity, tag, schedule retest, link a chain).

NameTypeReqDescription
body
chain_id
entry_idstringyes
method
retest_at
severity
status
tags
target_id
title
url

Structured output declared, but exposes no named fields.

No examples provided.

update_report ~34

Update a report draft (pass the fields to change).

NameTypeReqDescription
fieldsobjectyes
report_idstringyes

Structured output declared, but exposes no named fields.

No examples provided.

update_session ~54

Update a session (title/status/notes/goal/time).

NameTypeReqDescription
goal
notes
session_idstringyes
status
title
total_seconds

Structured output declared, but exposes no named fields.

No examples provided.

Common questions

What is the ASMHunter MCP server?

ASMHunter is an MCP server listed in the public MCP registry as app.asmhunter/asmhunter-mcp. Drive ASMHunter attack-surface monitoring from an AI agent: recon, scans, findings, reports. This page covers its PyPI package (asmhunter-mcp).

Is the ASMHunter MCP server safe to use?

ASMHunter scores 58 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 20 September 2026. 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 ASMHunter MCP server expose?

ASMHunter exposes 34 tools: search_programs, get_program, recommend_programs, get_watchlist, get_scope_changes, and 29 more. Their descriptions and schemas cost roughly 1,771 tokens of context every time the server is loaded.

Is the ASMHunter MCP server still maintained?

ASMHunter is still listed as active in the MCP registry. We last reached this channel on 20 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.