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.

Webhound

NPM · WEBHOUND-MCP · 2 COMPONENTS · SCANNED SEP 20

Budgeted reports and datasets with Hound, Webhound's DeepSeek V4 Pro + GPT-5.4 research harness.

0 this week 87 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
  • No install/post-install scripts declared.Pass
  • No production dependencies, so there is no dependency health to assess. View diagnostics → Pass
Provenance & Transparency71
  • Repository check failed: no source repository is declared. See how to fix → View diagnostics → Fail
  • Cryptographically verified build provenance (signed, bound to WebhoundAI/webhound-mcp). View diagnostics → Pass
  • Clear OSI-approved license (MIT).Pass
  • Actively maintained (last published 55 days ago).Pass
  • Disclosure check failed: no security disclosure policy was found in the source repository. See how to fix → Fail
Schema Quality & AI Usability81
  • 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
  • AI-judged instruction clarity (good).Pass
  • Context-footprint check failed: tool/resource definitions use about 4056 tokens (~126/item across 32 items; 30 tools + 2 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 Management90
  • Stability observed for 27 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage76
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 14% of tool parameters carry a description.Partial
  • Structured output schemas are declared (100% of tools); any adoption earns full credit.Pass
Tool Safety88
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • 1 of 2 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "webhound_uninstall" implies "uninstall" and declares readOnlyHint instead, contradicting what its own name says it does. See how to fix → Partial
  • An AI judge read all 32 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Install

How do I install the Webhound MCP server?

Webhound runs locally as an npm package, launched with npx -y webhound-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

npm · webhound-mcp

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

  • 20 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 87 to 90. That category is still filling its 30-day observation window: 26 days of observed history at the previous scan, 27 at this one. The score rises as the window fills, whether or not the server changes.

  • 18 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 80 to 83. That category is still filling its 30-day observation window: 24 days of observed history at the previous scan, 25 at this one. The score rises as the window fills, whether or not the server changes.

  • 16 Sept 26 −3
    • Stability: pass → 0.77 functional
  • 15 Sept 26 0
    • Stability: 0.97 → pass security
  • 14 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 at this one. The score rises as the window fills, whether or not the server changes.

  • 12 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 87 to 90. That category is still filling its 30-day observation window: 26 days of observed history at the previous scan, 27 at this one. The score rises as the window fills, whether or not the server changes.

  • 10 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 80 to 83. That category is still filling its 30-day observation window: 24 days of observed history at the previous scan, 25 at this one. The score rises as the window fills, whether or not the server changes.

  • 9 Sept 26 −3
    • Stability: pass → 0.80 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 npm/webhound-mcp@0.5.2

Provenance Verified

A signed build attestation was found and verified, binding this exact artifact to the source repository it claims to come from.

Result Verified
Ecosystem npm
Reason Verified
Discovered via Registry attestation endpoint
Source repo WebhoundAI/webhound-mcp
Certificate issuer https://token.actions.githubusercontent.com
Certificate SAN https://github.com/WebhoundAI/webhound-mcp/.github/workflows/publish.yml@refs/tags/v0.5.2
Rekor log index 2255214024
Predicate type https://slsa.dev/provenance/v1
Subject digest sha512:73ad08e585ff537724318cb91a262c00280155bc3675c540266485452d8dfa2e268cb5e08fe2f0265b0e5bbfe6a24f863b1af9640d2915480bfe2997a

Background: How many MCP packages publish verified provenance →

Dependencies 0 packages
Packages resolved 0
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 30 exposed · ~2,555 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
webhound_uninstall ~53

No-spend guidance for removing Webhound MCP config and Webhound-specific local rules from an agent workspace. Does not revoke keys automatically.

NameTypeReqDescription
clientstring
include_rules_cleanupboolean
NameTypeReqDescription
action_startedboolean
api_message
auto_recharge_enabledboolean
billing_url
blockedboolean
body
clientstring
client_labelstring
codestring
current_balancenumber
data
error
error_detailsobject
guidance_onlyboolean
key_revocation_notestring
likely_rule_locationsarray
messagestring
next_actionstring|null
next_actionsarray
no_spendboolean
okbooleanyes
original_toolstring
requirednumber
retry_after_user_confirmsobject
retryableboolean
revokes_keyboolean
schema_versionstringyes
session_startedboolean
status
stepsarray
suggested_user_facing_wordingstring
summarystringyes
toolstringyes
top_up_urlstring
user_message_templatestring

No examples provided.

webhound_update_sidecar_note ~165

Edit, restore, or dismiss one shared sidecar note. No spend. Does not interrupt the Planner/Executor/Verifier cycle and does not change session status.

NameTypeReqDescription
confidencestring
hypothesisbooleanSet true only when this is explicitly a hypothesis without source URLs.
note_idstringyes
session_idstringyes
source_urlsarraySource URLs backing the note. Required unless hypothesis=true.
statusstringSet to dismissed to remove it from future planner intake; set to pending to restore it.
suggested_anglestring
summarystringConcise sourced note or hypothesis for Webhound to consider later.
why_it_mattersstring
NameTypeReqDescription
action_startedboolean
api_message
auto_recharge_enabledboolean
billing_url
blockedboolean
body
codestring
current_balancenumber
data
error
error_detailsobject
interruptingboolean
messagestring
next_actionstring|null
next_actionsarray
no_spendboolean
noteobject
okbooleanyes
original_toolstring
requirednumber
retry_after_user_confirmsobject
retryableboolean
schema_versionstringyes
session_idstring
session_startedboolean
status
summarystringyes
toolstringyes
top_up_urlstring
updatedboolean
user_message_templatestring

No examples provided.

webhound_upload_file ~111

Upload a CSV, XLSX, PDF, DOCX, TXT, Markdown, or VTT ChatGPT attachment, local file, text, or base64 content for use in a report or dataset. Convert legacy XLS/DOC files to XLSX/DOCX first.

NameTypeReqDescription
content_base64string
file_namestring
filesarray
local_pathstring
mime_typestring
textstring
NameTypeReqDescription
action_startedboolean
api_message
auto_recharge_enabledboolean
billing_url
blockedboolean
body
codestring
current_balancenumber
data
error
error_detailsobject
extraction_statusstring
file_idstring
file_idsarray
file_namestring
filenamestring
filesarray
idstring
messagestring
mime_typestring
next_actionstring|null
next_actionsarray
no_spendboolean
okbooleanyes
original_toolstring
requirednumber
retry_after_user_confirmsobject
retryableboolean
schema_versionstringyes
session_startedboolean
sizeinteger
size_bytesinteger
status
summarystringyes
toolstringyes
top_up_urlstring
user_message_templatestring

No examples provided.

webhound_wait ~92

Bounded wait wrapper around webhound_watch. Max 110 seconds, then returns still_running if not terminal. still_running is normal for budgeted research; call wait/watch again unless status is awaiting_input or a blocking alert is present. Do not finalize or stop a healthy running session.

NameTypeReqDescription
max_wait_secondsinteger
poll_interval_secondsinteger
session_idstringyes
NameTypeReqDescription
acceptedboolean
action_requiredboolean
action_startedboolean
activityobject
agent_instruction
agents
alertsarray
amount_addednumber
api_message
assembly_triggeredboolean
auto_recharge_enabledboolean
billing_url
blockedboolean
body
budgetnumber
budget_control
checked_atstring
codestring
completion_reasonstring|null
completion_statestring
costnumber
credit_limitnumber
current_balancenumber
current_budgetnumber
current_spendnumber
data
dataset
documents
doneboolean
error
error_detailsobject
followup_check_in
forbidden_next_toolsarray
free_run
guidance_addedboolean
healthyboolean
is_runningboolean
kindstring
mcp_next_actionstring
messagestring
message_idstring
namestring
new_budgetnumber
next_actionstring|null
next_actionsarray
no_spendboolean
okbooleanyes
original_toolstring
output_readyboolean
polling
previous_budgetnumber
productstring
requirednumber
research_harnessstring
resumedboolean
retry_after_user_confirmsobject
retryableboolean
runtime_estimate
schema_versionstringyes
session_idstring
session_startedboolean
session_typestring
sidecar_guidance
status
status_snapshot
still_runningboolean
stoppedboolean
successful_completionboolean
summarystringyes
toolstringyes
top_up_urlstring
total_spentnumber
urlstring
user_message_templatestring

No examples provided.

webhound_watch ~53

Authoritative session watcher. done=true means the run is terminal. output_ready=true without done=true can still be intermediate; keep waiting unless the user explicitly asks for a partial update.

NameTypeReqDescription
session_idstringyes
NameTypeReqDescription
acceptedboolean
action_startedboolean
activityobject
agent_instruction
agents
alertsarray
amount_addednumber
api_message
assembly_triggeredboolean
auto_recharge_enabledboolean
billing_url
blockedboolean
body
budgetnumber
budget_control
checked_atstring
codestring
completion_reasonstring|null
completion_statestring
costnumber
credit_limitnumber
current_balancenumber
current_budgetnumber
current_spendnumber
data
dataset
documents
doneboolean
error
error_detailsobject
followup_check_in
forbidden_next_toolsarray
free_run
guidance_addedboolean
healthyboolean
is_runningboolean
kindstring
mcp_next_actionstring
messagestring
message_idstring
namestring
new_budgetnumber
next_actionstring|null
next_actionsarray
no_spendboolean
okbooleanyes
original_toolstring
output_readyboolean
previous_budgetnumber
productstring
requirednumber
research_harnessstring
resumedboolean
retry_after_user_confirmsobject
retryableboolean
runtime_estimate
schema_versionstringyes
session_idstring
session_startedboolean
session_typestring
sidecar_guidance
status
status_snapshot
stoppedboolean
successful_completionboolean
summarystringyes
toolstringyes
top_up_urlstring
total_spentnumber
urlstring
user_message_templatestring

No examples provided.

Common questions

What is the Webhound MCP server?

Webhound is an MCP server listed in the public MCP registry as ai.webhound/webhound. Budgeted reports and datasets with Hound, Webhound's DeepSeek V4 Pro + GPT-5.4 research harness. This page covers its npm package (webhound-mcp).

Is the Webhound MCP server safe to use?

Webhound scores 87 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 20 September 2026. It declares no install or post-install scripts. Its build provenance is signed and verified. 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 Webhound MCP server expose?

Webhound exposes 30 tools: webhound_health, webhound_onboarding, webhound_help, webhound_uninstall, webhound_get_defaults, and 25 more. Their descriptions and schemas cost roughly 2,555 tokens of context every time the server is loaded.

Is the Webhound MCP server still maintained?

Webhound 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.

What licence is the Webhound MCP server under?

Webhound declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.