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.

Weav

REMOTE · MCP.WEAV.COM

Sign up for Weav in chat, set up your AI agent, triage conversations, and manage your Help Center.

Available components

+43 this week 79 Trust /100

Last scanned (23 hours ago)

Scores higher than 74% of remote servers

Reachable. Last reached 21 Nov 2026.

Category CRM and Sales

Trust breakdown (7 categories)

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 Security89
Transport & Reachability100
Schema Quality & AI Usability85
  • 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
  • Tool/resource definitions use about 4734 tokens (~98/item across 48 items; 48 tools + 0 resources), lean.Pass
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management3
  • Stability observed for 1 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
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
  • All 7 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.Pass
  • An AI judge read all 49 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
What we tested

Checks we ran (13)

  • TLS certificate
  • Authorization
  • HTTPS
  • HSTS header
  • DNSSEC
  • Transport
  • Schema quality
  • Stability
  • Tool coverage
  • Injection markers
  • Destructive annotations
  • Judged manipulation
  • MCP protocol

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 →

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.

  • 21 Nov 26 0
    • Stability: unverified → 0.03 ▲ functional
  • 20 Nov 26 +43
    • Transport: unverified → pass ▲ security
    • Injection markers: unverified → pass ▲ security
    • First check of Judged manipulation: pass security
    • Authorization: Authorisation is enforced on tool calls, advertised via RFC 9728 protected-resource metadata. Discovery is public, which costs nothing: no tool can be invoked without a token. security
    • MCP protocol: unverified → pass ▲ functional
    • Schema quality: unverified → 100 ▲ functional
    • Tool coverage: unverified → 100 ▲ functional
    • First check of Schema quality: fail functional
    • First check of Destructive annotations: 100 functional
    • First check of Schema quality: pass functional
    • First check of Schema quality: good functional
    • First check of Tool coverage: 100 functional
  • 18 Nov 26 +18
    • Transport: fail → unverified ▼ security
    • Authorization: unverified → pass ▲ security
    • HTTPS: unverified → pass ▲ security
    • Tool safety: Tool safety blocked by authentication: the endpoint requires auth we don't have to read its tools. security
    • Tool coverage: Tool coverage blocked by authentication: the endpoint requires auth we don't have to read its tools. functional
    • Schema quality: Schema blocked by authentication: the endpoint requires auth we don't have to read it. functional
    • Capabilities: Capabilities blocked by authentication: the endpoint requires auth we don't have to read them. functional
  • 17 Nov 26 −18
    • Transport: unverified → fail ▼ security
    • HTTPS: pass → unverified ▼ security
    • Authorization: pass → unverified ▼ security
    • Tool safety: Tool safety not yet verified: we couldn't read the endpoint's tools, or could read only part of the list. security
    • Tool coverage: Tool coverage not yet verified: we couldn't read the endpoint's tools, or could read only part of the list. functional
    • Capabilities: Capabilities not yet verified: we couldn't read the endpoint's capabilities. functional
    • Schema quality: Schema not yet verified: we couldn't read the endpoint's schema, or could read only part of its tool list. 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
  • 28 Sept 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
  • 25 Sept 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
  • 27 Aug 26 0

    First indexed and scored.

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 21 Nov 2026 · Probed https://mcp.weav.com/mcp

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=weav.com CN=WE1,O=Google Trust Services,C=US 26 Sept 2026 25 Dec 2026 ECDSA 256 ECDSA-SHA256 6740a46f03519eb70e0c4a486e0ed7af
SANs: weav.com, *.weav.com
CN=WE1,O=Google Trust Services,C=US (CA) CN=GTS Root R4,O=Google Trust Services LLC,C=US 13 Dec 2023 20 Feb 2029 ECDSA 256 ECDSA-SHA384 7ff31977972c224a76155d13b6d685e3
CN=GTS Root R4,O=Google Trust Services LLC,C=US (CA) CN=GlobalSign Root CA,OU=Root CA,O=GlobalSign nv-sa,C=BE 15 Nov 2023 28 Jan 2028 ECDSA 384 SHA256-RSA 7fe530bf331343bedd821610493d8a1b

Background: What to check on a remote MCP endpoint →

DNSSEC insecure

Validation of mcp.weav.com. — Not signed

Zone DS Keys Algorithms Outcome
. Trust anchor 20326, 38696 8, 8 Verified
com. DS published 19718 13 Verified
weav.com. No DS Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation
Authentication Enforced and verified

The endpoint asked for a token and published valid RFC 9728 metadata describing how to get one.

Result Enforced and verified
Enforced On tool calls
HTTP status 200

WWW-Authenticate challenge Bearer realm="mcp", resource_metadata="https://mcp.weav.com/.well-known/oauth-protected-resource/mcp"

Bearer realm="mcp", resource_metadata="https://mcp.weav.com/.well-known/oauth-protected-resource/mcp"
Header Value
x-content-type-options nosniff
x-frame-options SAMEORIGIN

Protected resource metadata

Document https://mcp.weav.com/.well-known/oauth-protected-resource/mcp
Retrieved Yes
Resource https://mcp.weav.com/mcp
Authorisation server https://mcp.weav.com

Background: How OAuth 2.1 works in the 2026 MCP spec →

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://mcp.weav.com/mcp Verified 200
http (plaintext) http://mcp.weav.com/mcp HTTPS enforced 301 https://mcp.weav.com/mcp
MCP tools · 48 exposed · ~4,408 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_training_data ~152

Add Weav agent training data as text, Q&A, or a website URL. A website URL is crawled; every discovered page is trained. Every agent in the workspace is given access automatically.

NameTypeReqDescription
answerstring–Required when type is qa.
contentstring–Required when type is text.
questionstring–Required when type is qa.
titlestring–Optional title.
typestringyesKind of training data to add.
urlstring–Website URL to crawl. Weav discovers pages on the site and trains on all of them.
urlsarray–Specific pages to train without crawling. Use url for a whole website.

No output schema declared.

No examples provided.

create_checkout_link ~229

Create a Stripe Checkout link to subscribe to a plan or buy more AI credits. Nothing is charged until the user pays on the Stripe page. Plans: plus, pro, max (with interval monthly or yearly) and ai_credits (1,000-credit packs, needs a plan). Workspaces on credit billing (billing.credit_billing in get_setup_status) use credit_plan or credit_top_up instead. Confirm the choice with the user first. Always pass the setup_key from verify_signup_code on every setup call, even when OAuth is signed in; the key takes precedence over OAuth.

NameTypeReqDescription
intervalstring–Billing interval for plus, pro or max. Defaults to monthly.
purchasestringyesWhat to buy.
quantityinteger–Number of 1,000-credit packs for ai_credits. Defaults to 1.
setup_keystring–Pass the setup_key from verify_signup_code on EVERY setup call, even when OAuth is signed in to another workspace. It selects the workspace and takes precedence over OAuth. Omit only to use the OAuth…

No output schema declared.

No examples provided.

delete_training_data ~44

Delete an agent training data item in Weav. For website/URL sources this also deletes discovered URLs and chunks.

NameTypeReqDescription
training_data_idstringyesTraining data UUID.

No output schema declared.

No examples provided.

get_chat_widget_install ~117

Get the script that adds the Weav AI chat widget to the user's website, with install instructions. Share it with the user or their developer. Always pass the setup_key from verify_signup_code on every setup call, even when OAuth is signed in; the key takes precedence over OAuth.

NameTypeReqDescription
setup_keystring–Pass the setup_key from verify_signup_code on EVERY setup call, even when OAuth is signed in to another workspace. It selects the workspace and takes precedence over OAuth. Omit only to use the OAuth…

No output schema declared.

No examples provided.

get_conversation ~94

Get a Weav conversation, including recent messages. Pass conversation_id from search_conversations (that tool returns id). Do not use a customer, message, or other model id.

NameTypeReqDescription
conversation_idstring–Conversation ID from search_conversations (the id field on those results). Do not pass a customer, message, or other model id.
idstring–Alias for conversation_id. Prefer conversation_id.

No output schema declared.

No examples provided.

get_customer ~31

Get a Weav customer profile, company, and recent conversations.

NameTypeReqDescription
customer_idstringyesCustomer UUID.

No output schema declared.

No examples provided.

get_setup_status ~135

Get the workspace's setup checklist, the next step, AI credits left, and plans. Use it right after signup and whenever the user asks what to do next. Pass setup_key from verify_signup_code, or call it while signed in. Always pass the setup_key from verify_signup_code on every setup call, even when OAuth is signed in; the key takes precedence over OAuth.

NameTypeReqDescription
setup_keystring–Pass the setup_key from verify_signup_code on EVERY setup call, even when OAuth is signed in to another workspace. It selects the workspace and takes precedence over OAuth. Omit only to use the OAuth…

No output schema declared.

No examples provided.

get_training_data ~48

Get a single agent training data item that Weav AI agents answer from. Help Center articles are separate and use the kb_* tools.

NameTypeReqDescription
training_data_idstringyesTraining data UUID.

No output schema declared.

No examples provided.

get_training_status ~138

Check website training started with start_website_training: crawl status, pages found and trained, and how many training sources the workspace has. Always pass the setup_key from verify_signup_code on every setup call, even when OAuth is signed in; the key takes precedence over OAuth.

NameTypeReqDescription
setup_keystring–Pass the setup_key from verify_signup_code on EVERY setup call, even when OAuth is signed in to another workspace. It selects the workspace and takes precedence over OAuth. Omit only to use the OAuth…
training_session_idstring–training_session_id from start_website_training. Omit for the latest one.

No output schema declared.

No examples provided.

kb_create_article ~93

Search first with kb_search_articles and update an existing article instead of creating a duplicate. New articles are drafts by default; status=published publishes immediately.

NameTypeReqDescription
category_idstring–Optional Help Center category UUID.
positioninteger–Optional position within the category.
statusstring–New articles default to draft; published articles go live immediately.
translationsarrayyesAt least one translation.

No output schema declared.

No examples provided.

kb_create_category ~65

Create a category in the workspace Help Center.

NameTypeReqDescription
namestringyesCategory name.
positioninteger|null–Optional display position.
section_idstring|null–Optional UUID of a Help Center section.
slugstring|null–Optional URL slug.

No output schema declared.

No examples provided.

kb_create_section ~49

Create a section in the workspace Help Center.

NameTypeReqDescription
namestringyesSection name.
positioninteger|null–Optional display position.
slugstring|null–Optional URL slug.

No output schema declared.

No examples provided.

kb_delete_article ~72

Delete a Help Center article. This is destructive and soft-deletes the article. Read it first and pass its current expected_version.

NameTypeReqDescription
article_idstringyesUUID of the Help Center article to soft-delete.
expected_versionstring–Version returned by kb_get_article; prevents deleting a newer edit.

No output schema declared.

No examples provided.

kb_delete_article_translation ~95

Delete one locale translation from a Help Center article. This is destructive and an article must keep at least one translation. Read the article first and pass its current expected_version.

NameTypeReqDescription
article_idstringyesUUID of the Help Center article to update.
expected_versionstring–Version returned by kb_get_article; prevents deleting a newer edit.
localestringyesLocale translation to delete, such as en.

No output schema declared.

No examples provided.

kb_delete_category ~42

Delete a Help Center category. This is destructive; its articles become uncategorized.

NameTypeReqDescription
category_idstringyesUUID of the Help Center category to delete.

No output schema declared.

No examples provided.

kb_delete_section ~40

Delete a Help Center section. Categories assigned to it become unsectioned.

NameTypeReqDescription
section_idstringyesUUID of the Help Center section to delete.

No output schema declared.

No examples provided.

kb_edit_proposal ~130

Save a pending Help Center improvement proposal's title and Markdown without publishing. Keeps a new-article draft synchronized; updates leave the published article unchanged. Read with kb_get_proposal first. Use this rather than kb_update_article for suggestion drafts. Separate from agent training data.

NameTypeReqDescription
contentstringyesFull replacement Markdown, including image URLs and native components; at most 1,048,576 characters. Saving does not publish.
proposal_idstringyesUUID of the pending Help Center improvement proposal to edit.
titlestringyesFull replacement title, at most 255 characters.

No output schema declared.

No examples provided.

kb_get_article ~80

Get a full public Help Center knowledge base article, including translation content. This is separate from agent training data managed by the *_training_data tools.

NameTypeReqDescription
article_idstringyesUUID of the Help Center article to retrieve.
localestring–Optionally keep only this locale translation, such as en or en-US (maximum 10 characters).

No output schema declared.

No examples provided.

kb_get_article_revision ~73

Get full revision content for a Help Center public knowledge base article. This is separate from agent training data managed by the *_training_data tools.

NameTypeReqDescription
article_idstringyesUUID of the Help Center article that owns the revision.
revision_idstringyesUUID of the Help Center article revision to retrieve.

No output schema declared.

No examples provided.

kb_get_overview ~38

Get counts and locales for the workspace Help Center public knowledge base. This is separate from agent training data managed by the *_training_data tools.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

kb_get_preview_link ~138

Get a shareable link to preview a draft Help Center article or a pending KB proposal inside the whole Help Center. Anyone with the link can view it; it never expires and is not indexed. Pass `regenerate: true` to replace the link so the old one stops working.

NameTypeReqDescription
article_idstring–UUID of the draft Help Center article to preview. Provide exactly one of article_id or proposal_id.
proposal_idstring–UUID of the pending Help Center proposal to preview. Provide exactly one of article_id or proposal_id.
regenerateboolean–Replace the current link; the old link stops working.

No output schema declared.

No examples provided.

kb_get_proposal ~58

Get full details for an improvement proposal in the workspace Help Center public knowledge base. This is separate from agent training data managed by the *_training_data tools.

NameTypeReqDescription
proposal_idstringyesUUID of the Help Center improvement proposal to retrieve.

No output schema declared.

No examples provided.

kb_import_status ~124

Check a help center import started with kb_start_import: stage, article counts, verification, and the review link. Always pass the setup_key from verify_signup_code on every setup call, even when OAuth is signed in; the key takes precedence over OAuth.

NameTypeReqDescription
import_idstringyesimport.id from kb_start_import.
setup_keystring–Pass the setup_key from verify_signup_code on EVERY setup call, even when OAuth is signed in to another workspace. It selects the workspace and takes precedence over OAuth. Omit only to use the OAuth…

No output schema declared.

No examples provided.

kb_list_article_revisions ~122

List redacted revision summaries for a Help Center public knowledge base article. This is separate from agent training data managed by the *_training_data tools.

NameTypeReqDescription
article_idstringyesUUID of the Help Center article whose revisions to list.
limitinteger–Maximum revisions per page (1-50, default 20).
localestring–Optionally filter revisions to this locale, such as en or en-US (maximum 10 characters).
pageinteger–Page number to return (minimum 1, default 1).

No output schema declared.

No examples provided.

kb_list_articles ~153

List summaries of the workspace Help Center public knowledge base articles. This is separate from agent training data managed by the *_training_data tools.

NameTypeReqDescription
category_idstring–Filter to a Help Center category UUID. Do not combine with uncategorized.
limitinteger–Maximum articles per page (1-50, default 20).
localestring–Keep only translations for this locale, such as en or en-US (maximum 10 characters).
pageinteger–Page number to return (minimum 1, default 1).
statusstring–Filter by article status.
uncategorizedboolean–When true, include only articles without a Help Center category.

No output schema declared.

No examples provided.

kb_list_categories ~73

List categories in the workspace Help Center public knowledge base. This is separate from agent training data managed by the *_training_data tools.

NameTypeReqDescription
limitinteger–Maximum categories per page (1-50, default 20).
pageinteger–Page number to return (minimum 1, default 1).

No output schema declared.

No examples provided.

kb_list_proposals ~93

List improvement proposals for the workspace Help Center public knowledge base. This is separate from agent training data managed by the *_training_data tools.

NameTypeReqDescription
limitinteger–Maximum proposals per page (1-50, default 20).
pageinteger–Page number to return (minimum 1, default 1).
statusstring–Filter by proposal status; ignored proposals are omitted by default.

No output schema declared.

No examples provided.

kb_list_sections ~58

List sections in the workspace Help Center public knowledge base.

NameTypeReqDescription
limitinteger–Maximum sections per page (1-50, default 20).
pageinteger–Page number to return (minimum 1, default 1).

No output schema declared.

No examples provided.

kb_publish_article ~66

Publish a Help Center article immediately. Read the article first and pass its current expected_version.

NameTypeReqDescription
article_idstringyesUUID of the Help Center article to publish.
expected_versionstring–Version returned by kb_get_article; prevents publishing a newer edit with stale data.

No output schema declared.

No examples provided.

kb_reorder_articles ~67

Set the order of all articles in one Help Center category group.

NameTypeReqDescription
category_idstring|null–Category UUID to reorder. Omit or send null to reorder uncategorized articles.
idsarrayyesAll article UUIDs in the desired order for this category group.

No output schema declared.

No examples provided.

kb_reorder_categories ~36

Set the display order of all Help Center categories.

NameTypeReqDescription
idsarrayyesAll category UUIDs in the desired display order.

No output schema declared.

No examples provided.

kb_reorder_sections ~36

Set the display order of all Help Center sections.

NameTypeReqDescription
idsarrayyesAll section UUIDs in the desired display order.

No output schema declared.

No examples provided.

kb_restore_article_revision ~92

Restore an article translation to the selected prior revision, saving the current translation as a new revision first. Read the article first and pass its current expected_version.

NameTypeReqDescription
article_idstringyesUUID of the Help Center article to restore.
expected_versionstring–Version returned by kb_get_article; prevents restoring over a newer edit.
revision_idstringyesUUID of the revision to restore.

No output schema declared.

No examples provided.

kb_search_articles ~172

Search public Help Center knowledge base article titles and content. This is separate from agent training data; use search_training_data for data Weav AI agents answer from.

NameTypeReqDescription
category_idstring–Filter to a Help Center category UUID.
limitinteger–Maximum articles per page (1-50, default 20).
localestring–Search only this locale, such as en or en-US (maximum 10 characters).
pageinteger–Page number to return (minimum 1, default 1).
querystringyesSearch words or phrases from Help Center article titles and markdown content (1-255 characters).
statusstring–Filter by article status.
uncategorizedboolean–When true, include only articles without a Help Center category.

No output schema declared.

No examples provided.

kb_start_import ~186

Copy an existing public help center (Zendesk, Intercom, HelpScout, etc.) into the Weav Help Center knowledge base. The Help Center stays private until the user goes live. Only works while the Weav Help Center is empty and not live. Check progress with kb_import_status. Always pass the setup_key from verify_signup_code on every setup call, even when OAuth is signed in; the key takes precedence over OAuth.

NameTypeReqDescription
instructionsstring–Optional notes for the import, for example which sections to skip.
setup_keystring–Pass the setup_key from verify_signup_code on EVERY setup call, even when OAuth is signed in to another workspace. It selects the workspace and takes precedence over OAuth. Omit only to use the OAuth…
urlstringyesPublic URL of the existing help center, for example help.acme.com.

No output schema declared.

No examples provided.

kb_unpublish_article ~73

Unpublish a Help Center article and return it to draft. Read the article first and pass its current expected_version.

NameTypeReqDescription
article_idstringyesUUID of the Help Center article to unpublish.
expected_versionstring–Version returned by kb_get_article; prevents unpublishing after a newer edit.

No output schema declared.

No examples provided.

kb_update_article ~158

Update an existing Help Center article. Content edits to an existing locale save a revision; SEO-only edits do not. Adding a locale requires both title and content.

NameTypeReqDescription
article_idstringyesUUID of the Help Center article to update.
category_idstring|null–Optional category UUID. Send null to uncategorize; omit to keep the current category.
expected_versionstring–Version returned by kb_get_article; prevents overwriting a newer edit.
positioninteger–Optional position within the category.
statusstring–Optional new article status.
translationsarray–Optional locale edits. Content edits to existing locales save revisions; SEO-only edits do not. New locales require title and content.

No output schema declared.

No examples provided.

kb_update_category ~90

Update a Help Center category name, slug, or display position.

NameTypeReqDescription
category_idstringyesUUID of the Help Center category to update.
namestring–Optional category name.
positioninteger|null–Optional display position.
section_idstring|null–Optional UUID of a Help Center section; null clears it.
slugstring|null–Optional URL slug.

No output schema declared.

No examples provided.

kb_update_section ~70

Update a Help Center section name, slug, or display position.

NameTypeReqDescription
namestring–Optional section name.
positioninteger|null–Optional display position.
section_idstringyesUUID of the Help Center section to update.
slugstring|null–Optional URL slug.

No output schema declared.

No examples provided.

resync_training_data ~38

Re-scrape an existing URL agent training data item in Weav.

NameTypeReqDescription
training_data_idstringyesURL training data UUID.

No output schema declared.

No examples provided.

search_conversations ~105

Search Weav support conversations the same way the inbox does: only conversations with at least one message. Spam is excluded unless spam is true.

NameTypeReqDescription
channelstring–Filter by channel.
limitinteger–Maximum results to return (1-50).
querystring–Search subject, customer name, or email.
spamboolean–When true, return spam conversations instead of inbox conversations.
statusstring–Filter by conversation status.

No output schema declared.

No examples provided.

search_customers ~44

Search Weav customers by name or email.

NameTypeReqDescription
limitinteger–Maximum results to return (1-50).
querystring–Search name or email.

No output schema declared.

No examples provided.

search_training_data ~82

Search agent training data that Weav AI agents answer from by title, description, type, or source. Help Center articles are separate; use kb_search_articles.

NameTypeReqDescription
limitinteger–Maximum results to return (1-50).
querystring–Search title, description, or source.
typestring–Filter by training data type.

No output schema declared.

No examples provided.

send_reply ~40

Post a reply to a Weav conversation as a workspace teammate.

NameTypeReqDescription
contentstringyesReply body.
conversation_idstringyesConversation UUID.

No output schema declared.

No examples provided.

start_signup ~72

Sign the user up for a free Weav account without leaving the chat. Emails a 6-digit code to the address the user gives you. No sign-in needed. Next, call verify_signup_code with that code.

NameTypeReqDescription
emailstringyesThe user's work email. Ask the user for it; never guess.

No output schema declared.

No examples provided.

start_website_training ~150

Crawl the user's website and add its pages to the AI agent's private training data. Same as the website step of web onboarding; no AI credits are used. Runs in the background; check progress with get_training_status. Always pass the setup_key from verify_signup_code on every setup call, even when OAuth is signed in; the key takes precedence over OAuth.

NameTypeReqDescription
setup_keystring–Pass the setup_key from verify_signup_code on EVERY setup call, even when OAuth is signed in to another workspace. It selects the workspace and takes precedence over OAuth. Omit only to use the OAuth…
websitestringyesPublic website or docs URL, for example acme.com.

No output schema declared.

No examples provided.

update_conversation ~99

Update a Weav conversation status, priority, or assignee. Does not delete conversations.

NameTypeReqDescription
assignee_idstring–User or agent UUID. Omit to leave unchanged; send null to unassign.
assignee_typestring–Type of assignee when assignee_id is set.
conversation_idstringyesConversation UUID.
prioritystring–New priority.
statusstring–New status.

No output schema declared.

No examples provided.

verify_signup_code ~148

Check the 6-digit code from start_signup and create the user's Weav workspace. Returns a setup_key that the setup tools accept for 24 hours, so setup can continue in chat. If the email already has a workspace, tells you to have the user sign in instead. Always pass the setup_key from verify_signup_code on every setup call, even when OAuth is signed in; the key takes precedence over OAuth.

NameTypeReqDescription
codestringyesThe 6-digit code from the Weav email.
company_namestringyesThe user's company or brand name; used as the workspace name. Ask the user.
signup_tokenstringyessignup_token returned by start_signup.

No output schema declared.

No examples provided.

Install

How do I install the Weav MCP server?

Weav is a hosted endpoint at https://mcp.weav.com/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 · mcp.weav.com

# add to Claude Code
claude mcp add --transport http com-weav-mcp 'https://mcp.weav.com/mcp'
Common questions

What is the Weav MCP server?

Weav is an MCP server listed in the public MCP registry as com.weav/mcp. Sign up for Weav in chat, set up your AI agent, triage conversations, and manage your Help Center. This page covers its hosted endpoint (https://mcp.weav.com/mcp).

Is the Weav MCP server safe to use?

Weav scores 79 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 Weav MCP server expose?

Weav exposes 48 tools: start_signup, verify_signup_code, get_setup_status, start_website_training, get_training_status, and 43 more. Their descriptions and schemas cost roughly 4,408 tokens of context every time the server is loaded.

Does the Weav MCP server require authentication?

Yes. Weav asked us for credentials when we connected, so you will need to authorise it in your MCP client before it can do anything.

Is the Weav MCP server still maintained?

Weav 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 Weav MCP server?

VerifyMCP ran 13 checks on Weav, covering TLS certificate, Authorization, HTTPS, HSTS header and 9 more. 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.