MCP HeartbeatTHE MCP OBSERVATORY
Public workspace

Explore

Evidence for your next connection.

Independent measurements of remote MCP servers. Every observation has a timestamp.

Read-only probes

MCP server · Code & DevOps

Cyberimpact MCP by usefulapi

Read Cyberimpact members, groups and mailing results; add members, send opt-ins, create mailings.

Checks passed
14 / 22

0 failed · 8 not measured

Median response
68 ms

Median of successful probes over 7 days

30-day uptime
Not measured

Share of countable probes over 30 days, including daily rollups. Auth challenges are excluded.

Discovered tools
25

Tool definitions returned by this server

Independent monitoring

Health & checks

Status history

Outdated check

Last connection measurement is over 24 hours old. Current availability is unknown.

Last checked
Check summary by test group
Test areaPassedFailedUnmeasured
ConnectionCan a client connect and discover tools?
500
Reliability & speedDoes it respond consistently and quickly?
004
Access & authenticationWhat is required to use this server?
102
Tool qualityAre the tool definitions usable by an agent?
400
Publisher identityCan the publisher be traced to its source?
402

Unmeasured means there is not enough evidence to decide. How these checks work

Inspect individual checks 22 recorded

Core

  • Pass
    Reachable

    Latest probe returned HTTP 200 in 68 ms.

  • Pass
    Valid handshake

    protocolVersion 2025-11-25, serverInfo.name cyberimpact-mcp.

  • Pass
    Lists tools

    tools/list returned 25 tools.

  • Pass
    Current protocol

    Negotiated 2025-11-25. The bar is 2025-06-18 or newer.

  • Pass
    HTTPS

    The endpoint URL is https.

Performance

  • Not measured
    Fast (p50)

    Median latency 68 ms over 1 samples in 7 days. The bar is 1000 ms. Need at least 5 samples.

  • Not measured
    Consistent (p95)

    95th percentile 68 ms over 1 samples in 7 days. The bar is 3000 ms. Need at least 20 samples.

  • Not measured
    Reliable (uptime)

    1 of 1 attempts returned a tool list in 30 days (100%). The bar is 99%. Need at least 30 samples.

  • Not measured
    Stable tool list

    Fewer than two successful probes in 30 days, so tool-list stability is not measured.

Access

  • Pass
    Open access

    tools/list succeeded with no credential, and the record declares none.

  • Not measured
    Standard auth

    Auth is not required, so the OAuth metadata check does not apply.

  • Not measured
    Free tier cited

    No publisher quote has been checked.

Tools

  • Pass
    Tools described

    Every tool description is at least 20 characters.

  • Pass
    Valid input schemas

    Every inputSchema is a JSON Schema object.

  • Pass
    Parameters documented

    118 of 118 parameters have a description (100%). The bar is 80%.

  • Pass
    Safety hints

    Every tool sets readOnlyHint or destructiveHint.

Publisher

  • Pass
    Verified namespace

    Listed in the Official MCP Registry.

  • Pass
    Website matches publisher

    The website host matches the reverse-domain namespace.

  • Pass
    Source repo linked

    A repository URL is on file.

  • Not measured
    Repo owner matches

    This namespace is not an io.github login, so the owner comparison does not apply.

  • Pass
    Recently updated

    Updated 2026-11-10T23:34:09.173327Z, within 180 days.

  • Not measured
    Open-source licence

    The GitHub licence lookup has not returned an OSI result yet.

Start using Cyberimpact MCP by usefulapi

Connect to this server

Choose your client, copy the configuration, then enable the server in your client’s MCP settings.

Run this command in your terminal, then restart Claude Code.

Claude Code

claude mcp add --transport http cyberimpact-mcp-by-usefulapi https://cyberimpact.usefulapi.io/mcp

Capabilities

Tools 25

cyberimpact_add_member

WRITE: add a contact as a subscribed member WITHOUT a confirmation email (implied consent) and put it in the given groups; the contact can then be mailed. Only use it for people who really gave their consent (CASL); to ask the person to confirm first use cyberimpact_send_optin. A member that already exists is rejected by the API. Throttled by Cyberimpact; for many contacts use the app's import. POST /members.

Discovered
cyberimpact_add_member_to_groups

WRITE: add an existing member to more groups (existing group memberships are kept). Being in a group makes the member a recipient of mailings sent to it. Returns the member's groups after the update. POST /members/{key}/groups.

Discovered
cyberimpact_create_group

WRITE: create a new, empty group (mailing list). A public group can be offered on subscription forms; a private one is internal. Groups cannot be deleted through this server. POST /groups.

Discovered
cyberimpact_create_mailing

WRITE, SENDS EMAIL TO CUSTOMERS: create a mailing scheduled to be sent at send_at to every member of the chosen groups. It goes out for real unless it is cancelled in the Cyberimpact app before send_at. Only call it after the user has approved the subject, body, sender and groups, and set confirm_send to true. mail_from must be a validated sender address of the account. A mailing cannot be deleted through this server. POST /mailings.

Discovered
cyberimpact_create_template

WRITE: create a new email template from HTML and/or text. It is only saved in the account; nothing is sent. POST /templates.

Discovered
cyberimpact_get_account

Check the connection and show which Cyberimpact account the API token belongs to (username, email, account name). GET /ping.

Discovered
cyberimpact_get_batch

Status of a bulk batch job (NEW, PROCESSING or COMPLETED) and its result. Set show_error_details to list the per-member errors. GET /batches/{id}.

Discovered
cyberimpact_get_group

One group by id with its member count, mailing count and flags. GET /groups/{id}.

Discovered
cyberimpact_get_mailing

One mailing by id with its results: sent/delivered/stopped counts, views, clicks, delivery/click/view rates, per-link clicks, recipient groups, sender and body (HTML/text, cut at 20 000 characters). GET /mailings/{id}.

Discovered
cyberimpact_get_member

One member by email address or id: all attributes, consent type, mailings received/opened/clicked and custom fields (keyed by custom field id; see cyberimpact_list_custom_fields). GET /members/{key}.

Discovered
cyberimpact_get_member_consent

A member's consent record: consent type, relation type, consent date, expiration and proof (for CASL compliance checks). GET /members/{key}/consent.

Discovered
cyberimpact_get_member_groups

The groups a member belongs to (id, title, public/private, dynamic). GET /members/{key}/groups.

Discovered
cyberimpact_get_member_mailings

The mailings a member received (use it to see what a contact was sent and when). GET /members/{key}/mailings.

Discovered
cyberimpact_get_template

One template by id with its HTML and text body (cut at 20 000 characters). GET /templates/{id}.

Discovered
cyberimpact_list_bounced_members

Members whose last mailing hard-bounced (invalid addresses to clean up), with the bounce date. GET /members/bounced.

Discovered
cyberimpact_list_custom_fields

The account's custom member fields (id, name, type text/date/integer/decimal). Member customFields are keyed by these ids. GET /customfields.

Discovered
cyberimpact_list_group_members

The members of one group, with the same member filters as cyberimpact_list_members. GET /groups/{id}/members.

Discovered
cyberimpact_list_groups

List the account's groups (mailing lists) with member and mailing counts, public/private and dynamic flags. Use the ids to target mailings and opt-ins. GET /groups.

Discovered
cyberimpact_list_mailing_recipients

Who received a mailing and what happened: kind = all, delivered, stopped, hard_bounced, soft_bounced, unsubscribed, opened or clicked. Optionally only recipients from one group. GET /mailings/{id}/recipients[/{kind}].

Discovered
cyberimpact_list_mailings

List mailings by state: sent (default, archived ones excluded), scheduled (queued to go out) or archived. Each has id, subject, language, send/schedule date, recipient count and sender. Optionally only mailings sent to one group. GET /mailings/{sent|scheduled|archived}.

Discovered
cyberimpact_list_members

List subscribed contacts (members) with name, email, language, consent type, mailing counts and custom fields. status: active (in at least one group, default), orphans (in no group) or all. Filter by the date a member joined or was last updated. Bounced and unsubscribed members have their own tools. GET /members.

Discovered
cyberimpact_list_templates

List the account's email templates (id, title, created/updated). GET /templates.

Discovered
cyberimpact_list_unsubscribed_members

Members who unsubscribed, with the unsubscribe date. These contacts must not be mailed again. GET /members/unsubscribed.

Discovered
cyberimpact_send_optin

WRITE, SENDS AN EMAIL to the given address: an opt-in confirmation request. The person is added to the groups only after they confirm (the member is created if it does not exist). Use this instead of cyberimpact_add_member when you do not have the person's consent yet. Only call it after the user has approved sending to this address, and set confirm_send to true. Throttled by Cyberimpact. POST /members/optins.

Discovered
cyberimpact_update_member

WRITE: change only the given attributes of a member (other attributes stay as they are). The old values of the changed fields are overwritten and not recoverable through the API. Set new_email to change the address. PATCH /members/{key}.

Discovered

Recent measurements

Probe history

View status
Latest stored probes. Raw probe rows are kept for 14 days.
CheckedResultResponseTools
Connected68 ms25