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.

app.agendaforge/agendaforge

REMOTE · MCP.AGENDAFORGE.APP

Event management for organizers: events, sessions, speakers, agendas, forms, approval-gated writes.

0 this week 81 Trust /100

Last scanned (19 hours ago)

Scores higher than 83% of remote servers

Reachable. Last reached 6 Nov 2026.

Category Project Management

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 Security81
Transport & Reachability100
Schema Quality & AI Usability47
  • 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
  • AI-judged instruction clarity (poor).Fail
  • Context-footprint check failed: tool/resource definitions use about 9464 tokens (~169/item across 56 items; 55 tools + 1 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 Management100
  • No destabilizing schema changes in the last 30 days.Pass
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 Safety75
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • All 6 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.Pass
  • Manipulation check failed: an AI judge found 1 of 57 captured unit(s) of tool text manipulative, the first being "server instructions". See how to fix → Fail
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
  • Supports UI / widget rendering.Pass
What we tested

Checks we ran (13)

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

Checks we could not complete (1)

These are gaps on our side, not findings about this hosted endpoint. We only credit what we can confirm, so a category made up entirely of them scores 0.

  • HTTPS in Endpoint SecurityHTTPS enforcement could not be verified: the plaintext port answered with HTTP 401, which proves neither a plaintext path nor enforcement.

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.

  • 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
  • 26 Sept 26 0
    • Stability: fail → pass ▲ security
  • 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
  • 2 Sept 26 0
    • The server now declares the “resources” capability functional
    • First check of Capabilities: pass functional
    • First check of Schema quality: 100 functional
    • New resource “agenda_board” functional
  • 31 Aug 26 0
    • Judged manipulation: pass → fail ▼ security
    • The server rewrote its instructions, which are the text every model session reads security
    • Tool “add_contact_note” rewrote its description, which is the text the model reads security
    • Tool “assign_speaker” rewrote its description, which is the text the model reads security
    • Tool “check_in_attendee” rewrote its description, which is the text the model reads security
    • Tool “create_email_template” rewrote its description, which is the text the model reads security
    • Tool “create_event” rewrote its description, which is the text the model reads security
    • Tool “create_form” rewrote its description, which is the text the model reads security
    • Tool “create_session” rewrote its description, which is the text the model reads security
    • Tool “create_session_from_submission” rewrote its description, which is the text the model reads security
    • Tool “create_speaker_task” rewrote its description, which is the text the model reads security
    • Tool “create_sponsor” rewrote its description, which is the text the model reads security
    • Tool “decide_submission” rewrote its description, which is the text the model reads security
    • Tool “delete_session” rewrote its description, which is the text the model reads security
    • Tool “delete_sponsor” rewrote its description, which is the text the model reads security
    • Tool “import_contacts” rewrote its description, which is the text the model reads security
    • Tool “invite_to_portal” rewrote its description, which is the text the model reads security
    • Tool “manage_rooms” rewrote its description, which is the text the model reads security
    • Tool “manage_tracks” rewrote its description, which is the text the model reads security
    • Tool “remove_session_speaker” rewrote its description, which is the text the model reads security
    • Tool “request_media_upload” rewrote its description, which is the text the model reads security
    • Tool “schedule_session” rewrote its description, which is the text the model reads security
    • Tool “send_email” rewrote its description, which is the text the model reads security
    • Tool “send_speaker_message” rewrote its description, which is the text the model reads security
    • Tool “send_speaker_reminder” rewrote its description, which is the text the model reads security
    • Tool “set_submission_status” rewrote its description, which is the text the model reads security
    • Tool “update_contact” rewrote its description, which is the text the model reads security
    • Tool “update_form” rewrote its description, which is the text the model reads security
    • Tool “update_form_pipeline” rewrote its description, which is the text the model reads security
    • Tool “update_session” rewrote its description, which is the text the model reads security
    • Tool “update_sponsor” rewrote its description, which is the text the model reads security
    • Tool “invite_to_portal” is now declared destructive security
    • Tool “send_email” is now declared destructive security
    • Tool “send_speaker_message” is now declared destructive security
    • Tool “send_speaker_reminder” is now declared destructive security
    • Schema quality: 8571 → 9436 ▼ functional
    • Schema quality: excellent → poor functional
    • Destructive annotations: All 6 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation. functional
    • New tool “list_associated_contacts” functional
    • New tool “set_write_access” functional
    • “add_contact_note” reworded the description of “request_id” cosmetic
    • “assign_speaker” reworded the description of “request_id” cosmetic
    • “check_in_attendee” reworded the description of “request_id” cosmetic
    • “create_email_template” reworded the description of “request_id” cosmetic
    • “create_event” reworded the description of “request_id” cosmetic
    • “create_form” reworded the description of “request_id” cosmetic
    • “create_session” reworded the description of “request_id” cosmetic
    • “create_session_from_submission” reworded the description of “request_id” cosmetic
    • “create_speaker_task” reworded the description of “request_id” cosmetic
    • “create_sponsor” reworded the description of “request_id” cosmetic
    • “decide_submission” reworded the description of “request_id” cosmetic
    • “delete_session” reworded the description of “request_id” cosmetic
    • “delete_sponsor” reworded the description of “request_id” cosmetic
    • “import_contacts” reworded the description of “request_id” cosmetic
    • “invite_to_portal” reworded the description of “request_id” cosmetic
    • “manage_rooms” reworded the description of “request_id” cosmetic
    • “manage_tracks” reworded the description of “request_id” cosmetic
    • “remove_session_speaker” reworded the description of “request_id” cosmetic
    • “request_media_upload” reworded the description of “request_id” cosmetic
    • “schedule_session” reworded the description of “request_id” cosmetic
    • “send_email” reworded the description of “request_id” cosmetic
    • “send_speaker_message” reworded the description of “request_id” cosmetic
    • “send_speaker_reminder” reworded the description of “request_id” cosmetic
    • “set_submission_status” reworded the description of “request_id” cosmetic
    • “update_contact” reworded the description of “request_id” cosmetic
    • “update_form” reworded the description of “request_id” cosmetic
    • “update_form_pipeline” reworded the description of “request_id” cosmetic
    • “update_session” reworded the description of “request_id” cosmetic
    • “update_sponsor” reworded the description of “request_id” cosmetic
  • 27 Aug 26 0
    • Stability: unverified → fail ▼ security
    • A breaking change shipped without a version bump: still 1 ▼ security
    • Tool “get_speaker_card_link” was removed ▼ security
    • Tool “get_contact” rewrote its description, which is the text the model reads security
    • New tool “create_sponsor” functional
    • New tool “import_contacts” functional
    • New tool “list_sponsors” functional
    • “update_contact” reworded the description of “customFields” cosmetic
    • “update_session” reworded the description of “customFields” cosmetic
    • “update_sponsor” reworded the description of “customFields” cosmetic
  • 26 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 6 Nov 2026 · Probed https://mcp.agendaforge.app/mcp

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=agendaforge.app CN=WE1,O=Google Trust Services,C=US 23 Oct 2026 21 Jan 2027 ECDSA 256 ECDSA-SHA256 e016b0f6cdf81fe713650efbd0c0b7da
SANs: agendaforge.app, mcp.agendaforge.app, *.mcp.agendaforge.app
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.agendaforge.app. — Not signed

Zone DS Keys Algorithms Outcome
. Trust anchor 20326, 38696 8, 8 Verified
app. DS published 23684 8 Verified
agendaforge.app. 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 resource_metadata="https://mcp.agendaforge.app/.well-known/oauth-protected-resource/mcp"

Bearer resource_metadata="https://mcp.agendaforge.app/.well-known/oauth-protected-resource/mcp"

Protected resource metadata

Document https://mcp.agendaforge.app/.well-known/oauth-protected-resource/mcp
Retrieved Yes
Resource https://mcp.agendaforge.app/mcp
Authorisation server https://vigilant-gale-70.authkit.app

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

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://mcp.agendaforge.app/mcp Verified 200
http (plaintext) http://mcp.agendaforge.app/mcp Inconclusive 401
MCP tools · 55 exposed · ~9,327 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
update_contact ~452

Update a contact's profile fields, tags, or custom fields. Depending on the organization's settings, this either executes immediately or files a proposal for approval; the response status field says which happened.

NameTypeReqDescription
biostring–New biography.
companystring–New company.
contactIdstringyesThe contact id to update.
customFieldsobject–Key→value map of custom fields. Only include keys you want to add or change; existing custom fields are preserved (send a key with value null to remove it). You may key each entry by the field's disp…
eventIdstringyesEvent id, as returned by list_events.
expertiseAreasarray–Replacement list of the contact's areas of expertise.
firstNamestring–New first name.
jobTitlestring–New job title.
lastNamestring–New last name.
locationstring–New location.
orgstring–Organization slug. Only needed when you belong to multiple organizations; must be one returned by list_my_orgs.
phonestring–New phone number.
ratingnumber–A numeric rating/score for the contact.
request_idstringyesClient-generated unique id for this write (e.g. a UUID). Retries with the same request_id return the original executed or proposed outcome instead of creating a duplicate. Never reuse a request_id fo…
socialLinksobject–The contact's social profile links.
statusstring–The contact's status. 'archived' hides them; this is reversible.
tagsarray–Replacement list of free-text tags for the contact.
typestring–The contact's type/category.
websitestring–New personal website URL.

No output schema declared.

No examples provided.

update_form ~183

Conversationally edit a DRAFT form by instruction. Active forms are refused. Depending on the organization's settings, this either executes immediately or files a proposal for approval; the response status field says which happened.

NameTypeReqDescription
eventIdstringyesEvent id, as returned by list_events.
formIdstringyesThe draft form id to edit.
instructionstringyesThe natural-language edit instruction (e.g. 'rename the title', 'add a phone field').
orgstring–Organization slug. Only needed when you belong to multiple organizations; must be one returned by list_my_orgs.
request_idstringyesClient-generated unique id for this write (e.g. a UUID). Retries with the same request_id return the original executed or proposed outcome instead of creating a duplicate. Never reuse a request_id fo…

No output schema declared.

No examples provided.

update_form_pipeline ~168

Replace a form's submission pipeline stages (add, remove, rename, reorder). Depending on the organization's settings, this either executes immediately or files a proposal for approval; the response status field says which happened.

NameTypeReqDescription
eventIdstringyesEvent id, as returned by list_events.
formIdstringyesThe form id.
orgstring–Organization slug. Only needed when you belong to multiple organizations; must be one returned by list_my_orgs.
request_idstringyesClient-generated unique id for this write (e.g. a UUID). Retries with the same request_id return the original executed or proposed outcome instead of creating a duplicate. Never reuse a request_id fo…
statusesarrayyesThe full replacement pipeline stages array.

No output schema declared.

No examples provided.

update_session ~567

Update a session's content, taxonomy, schedule, or custom fields. Depending on the organization's settings, this either executes immediately or files a proposal for approval; the response status field says which happened.

NameTypeReqDescription
customFieldsobject–Key→value map of custom fields. Only include keys you want to add or change; existing custom fields are preserved (send a key with value null to remove it). You may key each entry by the field's disp…
descriptionstring–New session description.
durationnumber–New duration in minutes (recomputes end time if scheduled).
endTimestring–New end time as an ISO 8601 string.
eventIdstringyesEvent id, as returned by list_events.
formatstring–The format's exact NAME as returned by get_field_options (not free text).
isPublicboolean–Whether the session is public.
isTentativeboolean–Whether the session is tentative.
languagestring–The language's exact NAME as returned by get_field_options (not free text).
levelstring–The level's exact NAME as returned by get_field_options (not free text).
maxAttendeesnumber–New maximum attendee capacity.
orgstring–Organization slug. Only needed when you belong to multiple organizations; must be one returned by list_my_orgs.
request_idstringyesClient-generated unique id for this write (e.g. a UUID). Retries with the same request_id return the original executed or proposed outcome instead of creating a duplicate. Never reuse a request_id fo…
roomstring–The room's exact NAME as returned by get_field_options (not free text).
sessionIdstringyesThe session id to update.
startTimestring–New start time as an ISO 8601 string.
statusstring–The status's exact NAME as returned by get_field_options (not free text).
tagsarray–Replacement list of PREDEFINED tag names for the session. Each must exactly match a tag from get_field_options — tags are not free text.
titlestring–New session title.
trackstring–The track's exact NAME as returned by get_field_options (not free text).
typestring–New session type.

No output schema declared.

No examples provided.

update_sponsor ~318

Update a sponsor's details or custom fields. Depending on the organization's settings, this either executes immediately or files a proposal for approval; the response status field says which happened.

NameTypeReqDescription
customFieldsobject–Key→value map of custom fields. Only include keys you want to add or change; existing custom fields are preserved (send a key with value null to remove it). You may key each entry by the field's disp…
descriptionstring–New sponsor description.
eventIdstringyesEvent id, as returned by list_events.
hasBoothboolean–Whether the sponsor has a booth.
namestring–New sponsor name.
orgstring–Organization slug. Only needed when you belong to multiple organizations; must be one returned by list_my_orgs.
request_idstringyesClient-generated unique id for this write (e.g. a UUID). Retries with the same request_id return the original executed or proposed outcome instead of creating a duplicate. Never reuse a request_id fo…
sponsorIdstringyesThe sponsor id to update.
websitestring–New sponsor website URL.

No output schema declared.

No examples provided.

Install

How do I install the app.agendaforge/agendaforge MCP server?

app.agendaforge/agendaforge is a hosted endpoint at https://mcp.agendaforge.app/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.agendaforge.app

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

What is the app.agendaforge/agendaforge MCP server?

app.agendaforge/agendaforge is an MCP server listed in the public MCP registry as app.agendaforge/agendaforge. Event management for organizers: events, sessions, speakers, agendas, forms, approval-gated writes. This page covers its hosted endpoint (https://mcp.agendaforge.app/mcp).

Is the app.agendaforge/agendaforge MCP server safe to use?

app.agendaforge/agendaforge scores 81 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 app.agendaforge/agendaforge MCP server expose?

app.agendaforge/agendaforge exposes 55 tools: list_my_orgs, list_events, get_event, list_sessions, get_session, and 50 more. Their descriptions and schemas cost roughly 9,327 tokens of context every time the server is loaded.

Does the app.agendaforge/agendaforge MCP server require authentication?

Yes. app.agendaforge/agendaforge 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 app.agendaforge/agendaforge MCP server still maintained?

app.agendaforge/agendaforge is still listed as active in the MCP registry. We last reached this channel on 6 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 app.agendaforge/agendaforge MCP server?

VerifyMCP ran 13 checks on app.agendaforge/agendaforge, covering TLS certificate, Authorization, HSTS header, DNSSEC and 9 more. One item could not be completed, a gap on our side rather than a finding about app.agendaforge/agendaforge: HTTPS. 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.