Spec Driven Development
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Beschreibung vom Entwickler (englisches Original)
CallRail REST API v3: 57 tools for calls, leads, trackers, tags, users, and agency reporting.
Diese drei werden nie zu einer Punktzahl zusammengefasst: Meinungen, Messungen und Beliebtheit sind verschiedene Dinge.
Für diesen Server haben wir noch keine Zusammenfassung in einfacher Sprache geschrieben. Unten stehen die Fakten, die wir aus der Registry gelesen haben.
Wähle die KI-App, die du nutzt, und kopiere die Einstellungen.
CALLRAIL_API_KEYAls geheim markierte Werte sind Schlüssel zu deinem Konto. Gib sie nie weiter und füge sie nie in einen Chat ein.
Du brauchst
Welche App nutzt du?
Wähle oben deine App. Wir merken sie uns, damit der Button beim nächsten Mal „In … installieren“ anzeigt.
Öffne Claude Desktop → Settings → Developer → Edit Config und füge dies in claude_desktop_config.json ein
{
"mcpServers": {
"callrail": {
"command": "uvx",
"args": [
"callrail-mcp"
],
"env": {
"CALLRAIL_API_KEY": "your-value"
}
}
}
}Führe das in deinem Terminal aus
claude mcp add callrail --env CALLRAIL_API_KEY=your-value -- uvx callrail-mcpTrag die leeren Werte ein, bevor du ihn startest.
In .cursor/mcp.json in deinem Projekt oder in ~/.cursor/mcp.json einfügen
{
"mcpServers": {
"callrail": {
"command": "uvx",
"args": [
"callrail-mcp"
],
"env": {
"CALLRAIL_API_KEY": "your-value"
}
}
}
}Dein Browser fragt, ob er die App öffnen darf, dann zeigt die App die Einstellungen und bittet dich um Bestätigung. Schlüsselwerte bleiben leer, damit du sie selbst einträgst.
In .vscode/mcp.json in deinem Projekt einfügen
{
"servers": {
"callrail": {
"type": "stdio",
"command": "uvx",
"args": [
"callrail-mcp"
],
"env": {
"CALLRAIL_API_KEY": "your-value"
}
}
}
}Dein Browser fragt, ob er die App öffnen darf, dann zeigt die App die Einstellungen und bittet dich um Bestätigung. Schlüsselwerte bleiben leer, damit du sie selbst einträgst.
Dieser Server läuft auf deinem Computer, und ChatGPT kann sich nur mit Servern im Internet verbinden. Wähle eine andere App.
Deine Auswahl bleibt in einem Cookie auf diesem Gerät; kein Konto nötig.
Diese Einstellungen werden aus dem Registry-Eintrag des Entwicklers erzeugt. Wenn in der README etwas anderes steht, folge der README.
Läuft auf deinem Computer; die Tool-Liste erscheint nach der Installation in deiner KI-App.
Wir prüfen Informationen, die jeder sehen kann; den Code haben wir nicht gelesen. Checks, die nicht zutreffen, werden nicht mitgezählt. · Geprüft am 7. Nov. 2026
Der Registry-Name wurde mit dem GitHub-Konto pghdma bestätigt, dem das Repo gehört
Dieses Repo haben wir noch nicht von GitHub gelesen
Dieses Repo haben wir noch nicht von GitHub gelesen
Dieser Server läuft auf deinem Computer; es gibt keinen Endpunkt im Internet
Läuft auf deinem Computer und nutzt stattdessen lokale Einstellungen
Läuft auf deinem Computer; Tool-Listen können wir nur von Endpunkten im Internet lesen
Verglichen mit allen aktiven Servern dieser Kategorie in der Registry. Sterne zählen nur, wenn dem Herausgeber das Repo gehört.
Er hat 1 von 1 zutreffenden Basischecks bestanden. Den Code haben wir nicht gelesen. Bevor du einen Schlüssel oder Token hinzufügst, sieh nach, welche Zugriffe der Server verlangt, und nutze einen Schlüssel, der nur die Berechtigungen hat, die du brauchst.
Das musst du eintragen: CALLRAIL_API_KEY
Er läuft auf deinem Computer. Deine KI-App startet ihn bei Bedarf, und die Daten laufen nicht über die Server des Entwicklers (außer der Server ruft selbst einen Onlinedienst auf).
Das GitHub-Repo wurde zuletzt – geändert, und die neueste Version (1.3.1) kam vor 29 Tagen in die Registry.
Apps, die MCP unterstützen, etwa Claude Desktop, Claude Code, Cursor und VS Code. Außerdem brauchst du Python (uv) auf deinem Computer.
In derselben Kategorie: Spec Driven Development, Remote Desktop Commander, MemberVault MCP by usefulapi
Server derselben Kategorie von anderen Entwicklern, sortiert nach Sternen.
So liest du eine Karte:★ GitHub-SterneiDrei Säulen: Bewertungen · Checks · NutzungiAktualisiert = neueste Version in der Registry veröffentlichti
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Remote Desktop Commander: use files, terminal and processes on your own computers from any AI app.
List courses; add users to courses, remove course access or delete users in MemberVault.
Unverändert aus dem Repo des Entwicklers übernommen. PopNx MCP hat den Inhalt weder geprüft noch empfiehlt es ihn. HTML, Bilder und Skripte wurden entfernt. Links führen von dieser Website weg.
A Model Context Protocol server for the CallRail REST API v3. Point Claude Code, Claude Desktop, Cursor, or any other MCP client at it and ask about your call tracking in plain English.
I'm [Steve Japalucci](https://github.com/pghdma). I run Pittsburgh Digital Marketing Agency (PGHDMA), and I built this for my own client work. CallRail bills per tracking number and per minute across every client I manage, and I was tired of clicking through its reports to answer questions like "which client is burning my minutes this month". Now I ask Claude.
Works with both major versions of the MCP Python SDK (1.x and 2.x).
These are the kinds of questions I ask it every week:
Reporting
Agency cost attribution
Conversion debugging
Lead management
Tag and tracker management
confirm_billing=True, costs about $3/mo)# Recommended: pipx for an isolated CLI install
pipx install callrail-mcp
pip install callrail-mcp
To install from source (latest unreleased):
pipx install git+https://github.com/pghdma/callrail-mcp.git
Get an API key at Settings > API Keys in your CallRail account. You need Account Admin permission to create one.
Provide it one of two ways:
export CALLRAIL_API_KEY="your_key_here"
mkdir -p ~/.config/callrail
echo "your_key_here" > ~/.config/callrail/api-key.txt chmod 600 ~/.config/callrail/api-key.txt
Or override with CALLRAIL_API_KEY_FILE=/path/to/key.txt.
Every tool resolves the account id with one GET /a.json per process and caches it. Set CALLRAIL_ACCOUNT_ID to skip that lookup, or to pin one account when the key can see several.
~/.claude.json or claude_desktop_config.json){
"mcpServers": { "callrail": { "command": "callrail-mcp", "env": { "CALLRAIL_API_KEY": "your_key_here" } } } }
If you installed via pipx, callrail-mcp will be on your PATH automatically. Otherwise, point command at the full path to the executable.
The server speaks standard MCP stdio. Any client that supports stdio MCP servers will work; just run callrail-mcp as the command.
57 tools total, covering roughly 95% of CallRail's REST API v3 surface: read tools, write tools, tracker provisioning, agency aggregation, account management, notifications, integrations discovery, outbound calls, offline-lead backfill, leads and cross-channel timelines, SMS-thread lead management, and server-side analytics.
| Tool | Purpose |
|---|---|
list_accounts | List accessible CallRail accounts. fields="numeric_id" adds the number shown in CallRail URLs |
list_companies | List companies (clients) under an account. Optional status="active", search, fields (for example verified_caller_ids) and page |
list_trackers | List tracking phone numbers and their source mapping. Optional status="active", type, search and fields |
get_tracker | Full detail for one tracker |
list_calls | Paginated call list. Filter by company, date window, answer_status, direction, device, call_type, lead_status, tracker_id, tags and free-text search, with sort/order and an IANA time_zone |
get_call | Full detail for a specific call |
call_summary | Aggregate stats (total, answered by a person, voicemail, missed, by source, duration) for a window |
list_form_submissions | CallRail Form Tracking submissions. Filter by lead_status, tags and person_lead; sort by submitted_at or form_url |
list_text_messages | SMS conversations |
list_users | Account users, paginated. Filter by company_id, search names and emails, sort by email or created_at |
get_call_recording | Recording URL (if recording enabled). CallRail documents the link as good for at least 24 hours; HIPAA accounts get a temporary URL that expires in about 24 hours |
get_call_transcript | Transcript plus conversational_transcript, call_summary, call_highlights, keywords_spotted, sentiment and speaker_percent via field selection (Premium Conversation Intelligence required since 2026-05-21) |
search_calls_by_number | Find calls by phone number across a window (narrowed server-side with search, then matched exactly) |
list_tags | List tags in an account or filtered to one company. Filter by status and tag_level |
| Tool | Purpose |
|---|---|
update_call | Update note, tags, spam flag, customer name, lead status |
add_call_tags / remove_call_tags | Additive and subtractive tag changes (preserves existing) |
update_form_submission | Note, tags (replace, or add with append_tags=True), value (sent as the currency string CallRail documents) and lead status. Form submissions have no spam flag |
create_tag / update_tag / delete_tag | Full CRUD on company-level and account-level (tag_level="account") tags. update_tag can also disable or re-enable a tag |
| Tool | Purpose |
|---|---|
create_tracker | Provision a new tracking number. Requires `confirm_billing=True` as a safety guard against accidental provisioning. Supports source trackers and session (DNI) pools of 4 to 50 numbers. Source-specific fields are validated per type (search_engine and search_type for search, landing for the landing types, referrer for web_referrer), plus swap_targets and campaign_name |
update_tracker | Update mutable settings: name, destination, whisper, greeting (text or recording URL), recording flag, SMS, swap targets, campaign name. Reads the current call flow and merges your change into it, and refuses to overwrite an advanced (IVR) flow |
delete_tracker | Soft-delete a tracker (releases the phone number, preserves history) |
| Tool | Purpose |
|---|---|
get_company / create_company / update_company / delete_company | Full company (client) CRUD. Free, since CallRail bills per number rather than per company. Soft-delete semantics. Feature toggles go through the documented PUT fields (also right after create_company, since POST accepts only name and time zone); lead_scoring_enabled is read-only in the API and the deprecated no-op toggles are dropped with a warning |
get_user / create_user / update_user / delete_user | Full user CRUD. create_user invites by email; roles: admin, manager, reporting. update_user changes names and company access only, because the API cannot change a user's role or email |
get_tag | Single tag detail |
get_form_submission | Single form-submission detail |
get_text_message | Single SMS conversation with all messages |
create_form_submission | Manually create a form submission (backfill walk-in, paper-form, or offline leads). Requires form_url and form_data, attribution via session_id or the referrer trio; note, tags, value and lead status are applied with a follow-up update |
| Tool | Purpose |
|---|---|
list_notifications / create_notification / update_notification / delete_notification | Full per-user alert-rule CRUD (who gets pinged on which call, text, or form event) |
list_integrations(company_id) / get_integration | Discover GMB, Google Ads, Facebook, Slack, and Webhook integrations attached to a company. CallRail models webhooks as an integration type, so this is also how you inspect webhooks |
| Tool | Purpose |
|---|---|
create_outbound_call | Place an outbound call. CallRail dials business_phone_number first, then bridges to customer_phone_number, showing caller_id. Requires `confirm_dialing=True` as a safety guard, since it dials real phones, costs minutes, and carries legal implications. US and Canada only. Optional agent_id assigns the call to a user |
| Tool | Purpose |
|---|---|
list_leads / get_lead_timeline | CallRail's deduplicated person records (sortable by created_at, name or email), plus full cross-channel history (calls, forms, texts) per lead with first and last touch attribution |
list_sms_threads / get_sms_thread / update_sms_thread | SMS-thread lead management: tag, note, and qualify texting leads the way you would calls. Threads can be windowed by date and searched by number, name or tag |
call_stats | Server-side call aggregation via /calls/summary.json. Group by company, company_id, source, keywords, campaign, referrer, landing_page, or last_requested_page in one request instead of paginating every call. Takes the same server-side filters as list_calls (answer_status, direction, device, lead_status, first_time_callers, duration bounds, tags, tracker_ids, search, time_zone) |
call_timeseries | Call-volume trend line. Supports interval (hour, day, week, month, year), the same filters as call_stats, and guards CallRail's 200-data-point limit before sending |
form_stats | Server-side form-submission totals. group_by (source, keywords, campaign, referrer, landing_page, form_name, company), fields (total_forms, first_forms, leads), lead_status and tags |
get_call_page_views | The visitor's page-view journey behind a call. Pairs with call_eligibility_check for conversion debugging |
| Tool | Purpose |
|---|---|
usage_summary | Per-company cost-attribution breakdown for the cycle: minutes used, active numbers, estimated cost share, sorted by biggest cost driver. Answers "which client is burning my CallRail budget" |
call_eligibility_check | Audit whether a specific call qualifies as a Google Ads conversion. Checks gclid presence, answered status, duration against Google's threshold (default 60s), and source |
compare_periods | Compare the current N-day window against the previous one. Per-company minute and call deltas plus biggest mover |
| bulk_update_calls | Apply one update (tag, note, lead_status, spam) to every call matching a filter. `dry_ru
Nur der Anfang wird gezeigt; den Rest findest du im Repo