Un URL dà a Claude, ChatGPT, Cursor, Codex o al tuo agente 77 strumenti per pubblicare, programmare, creare grafiche e fare report su 13 social.
{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":"2025-06-18"}}
La tua AI saluta e indica la versione di MCP che parla.
{"jsonrpc":"2.0","id":1,"result":{"protocolVersion":"2025-06-18","serverInfo":{"name":"robinreach","title":"RobinReach"},"capabilities":{"tools":{}},"instructions":"RobinReach is a social media scheduling tool..."}}
RobinReach concorda la versione e manda note su come usare i suoi strumenti, più le impostazioni sulla voce del tuo brand.
{"jsonrpc":"2.0","id":2,"method":"tools/list"}
Chiede cosa può fare.
{"jsonrpc":"2.0","id":2,"result":{"tools":[{"name":"account_status"},{"name":"posts_validate"},{"name":"posts_create"}, … 74 more]}}
Riceve 77 strumenti, ognuno con una descrizione e i dati che gli servono.
{"jsonrpc":"2.0","id":3,"method":"tools/call","params":{"name":"posts_validate","arguments":{"social_profile_ids":[41,57],"content":"Speckled mugs are back on Friday."}}}
Prima di salvare qualsiasi cosa, controlla il post per Instagram e LinkedIn.
{"status":"success","message":"All validation checks passed. Ready to create."}
RobinReach conferma che il post rispetta le regole di ogni social.
{"jsonrpc":"2.0","id":4,"method":"tools/call","params":{"name":"posts_create","arguments":{"social_profile_ids":[41,57],"content":"Speckled mugs are back on Friday.","post_status":"scheduled","publish_time":"2026-11-06T09:00","timezone":"America/New_York"}}}
Programma il post per venerdì alle 9:00, ora di New York.
{"success":true,"post_id":18342,"status":"scheduled","platforms":["instagram","linkedin"],"message":"Post scheduled for November 6 at 9:00 AM EST."}
Il post è nel calendario di entrambi i social.
Uno scambio reale con ID di esempio. Ogni messaggio è un POST allo stesso URL.
Un endpoint, un accesso o una chiave, JSON-RPC semplice. Se il tuo strumento parla MCP via HTTP, può parlare con RobinReach.
https://robinreach.com/mcp/v1/messages
POST /mcp/v1/messages su robinreach.com. Ogni messaggio JSON-RPC va a questo unico URL.S256), registrazione dinamica del client e discovery tramite .well-known, così l'utente incolla solo l'URL. Ogni altro client invia una chiave API come Authorization: Bearer, oppure aggiunge ?api_key= all'URL.GET restituisce 405 perché il server non invia mai nulla di sua iniziativa, e OPTIONS risponde ai preflight CORS da qualsiasi origine.initialize, ping, tools/list e tools/call. Le notifiche ricevono 202 Accepted.brand_id). Una chiave brand raggiunge un solo brand e non ha bisogno di brand_id. Una connessione OAuth è l'una o l'altra cosa: l'utente sceglie tutto l'account o un solo brand quando accede.initialize restituisce note d'uso per il modello, più tono, missione, lingua e fuso orario del brand, così i post suonano giusti fin dalla prima chiamata.Questo elenco nasce dallo stesso registro con cui il server risponde a tools/list, quindi è sempre aggiornato.
77 di 77 strumenti
posts_validate
Post e programmazione
Validate post content/platform_options before creating, updating, or publishing. Always call this first. Fix any returned errors and re-validate before posts_create / posts_update / posts_publish_now. Pass post_id when validating changes to an existing post so validation checks its already-attached media (e.g. an Instagram post with no new media_urls but existing images) instead of assuming no media is attached.
social_profile_ids
8 parametri facoltativi
posts_create
Post e programmazione
Create and schedule (or save as draft) a post across one or more social profiles. Call posts_validate first.
social_profile_ids
12 parametri facoltativi
posts_update
Post e programmazione
Update an existing, unpublished post. Call posts_validate first with the merged content/options. media_urls is APPEND-ONLY by default; pass replace_media: true to replace existing attachments instead of adding to them. A library url whose file is already on the post is not added again (it is listed in media_already_attached). labels is also APPEND-ONLY by default; pass replace_labels: true to replace the post's entire label set instead of merging into it.
post_id
12 parametri facoltativi
posts_publish_now
Post e programmazione
Prima conferma
Publish a draft/scheduled/approved post immediately. Always show the content preview and get explicit user confirmation first.
post_id
1 parametro facoltativo
posts_delete
Post e programmazione
Prima conferma
Permanently delete a post. Always confirm with the user first.
post_id
1 parametro facoltativo
posts_delete_from_platform
Post e programmazione
Prima conferma
Delete a published post from specific social platforms (same as the dashboard's Delete from Platform). Supported: Facebook, LinkedIn, X, Threads, Telegram, Bluesky, Pinterest, YouTube, WordPress, Mastodon. Always confirm with the user first.
post_idsocial_profile_ids
1 parametro facoltativo
posts_reschedule
Post e programmazione
Change the publish_time of a scheduled post.
post_idnew_publish_time
1 parametro facoltativo
posts_list
Post e programmazione
List posts for a brand, optionally filtered by status and/or labels (matches ANY given label). Paginated, 10 per page.
posts_get_status
Post e programmazione
Get per-platform publish status for a post, with suggested fixes for any failures.
post_id
1 parametro facoltativo
posts_bulk_create
Post e programmazione
Create up to 20 posts in one call. Each post is validated independently; partial failures are reported per-index.
posts
1 parametro facoltativo
media_search
Immagini e media
Search the media library by filename, optionally scoped to a folder. Call media_folders first to confirm the exact folder name. Returns metadata and a URL only, NOT the image content. Call media_view before writing a caption for, or describing, any specific result; never guess content from the filename.
media_view
Immagini e media
The only way to actually see image content (returns downscaled base64, up to 10 at once). ALWAYS call this before writing a caption for, or describing, a specific image; never guess from a filename like 'big.jpg'.
media_folders
Immagini e media
List media library folders with attachment counts.
media_search_unsplash
Immagini e media
Search Unsplash for stock photos. Credit the photographer when used.
query
media_generate_ai_image
Immagini e media
Generate an AI image from a text prompt and save it to the media library. Optionally choose model: "gpt_image" (default) or "nano_banana_pro", and size (defaults to 1024x1024). Pass post_id to attach it directly to a post (add replace_media: true to replace that post's existing media instead of appending). Check quota first; fall back to media_search_unsplash if low.
image_prompt
5 parametri facoltativi
media_upload
Immagini e media
Download a public file_url into the media library. Returns job_id; poll media_upload_status a few seconds later to get the final url before using it in media_urls.
file_url
3 parametri facoltativi
media_upload_status
Immagini e media
Check the status of a media_upload job_id.
job_id
1 parametro facoltativo
media_direct_upload_create
Immagini e media
Start a direct upload for a local file with no public URL yet (screenshots, videos). Returns a signed upload_url; PUT the raw file bytes there immediately (it expires in minutes), then call media_direct_upload_finalize.
content_typebyte_sizechecksum
2 parametri facoltativi
media_direct_upload_finalize
Immagini e media
Finalize a direct upload after PUTting the file bytes, using the signed_id from media_direct_upload_create. Returns the permanent attachment url. Safe to retry: finalizing the same signed_id again returns the same attachment.
signed_id
2 parametri facoltativi
media_upload_from_chat
Immagini e media
Upload image/video files attached directly in this chat (e.g. an image you just generated) into the RobinReach media library. Put each file in its own field, file_1 to file_5 (call again for more than five); never ask the user for a public URL for these. Returns library URLs; use them in media_urls on posts_create / posts_update / posts_bulk_create.
analytics_get
Statistiche
Get raw engagement metrics for one social profile over a date range (default: last 30 days). A Google Business Profile answers with Google's own daily numbers under business (profile views on Search and Maps, website clicks, calls, direction requests, conversations, bookings, menu clicks) and post_analytics false, since Google has no per-post numbers.
social_profile_id
4 parametri facoltativi
analytics_top_posts
Statistiche
Get the best-performing posts by engagement over a date range.
analytics_calendar
Statistiche
Get the next 14 days of scheduled posts, with any gap days flagged.
analytics_performance_summary
Statistiche
Compare this week's engagement and post count to last week's, with a plain-language recommendation.
analytics_post
Statistiche
Get live engagement metrics for a published post, across every profile it was published to (or one specific profile if social_profile_id is given). Aggregates per-platform results. A result with `warnings` is missing some metrics (for example a Facebook Reel's views): tell the user which and why. X (Twitter) numbers are not live: they are the ones RobinReach read 1, 3 and 7 days after publishing, on the Scale plan.
post_id
2 parametri facoltativi
comments_list
Commenti
List comment threads across social profiles, sorted by most recent, with unread counts. A thread is one post's comment section. Each thread has likeable (whether comments_like works on it), last_comment (the newest message, which may be the brand's own reply), and recent_comments: the newest comments from other people, up to 5, each with external_id and liked (incoming_count is the full total). Goodwill comments (thanks, hearts, emoji, congratulations) usually deserve a like rather than a reply; group them and offer to like them with comments_like.
comments_reply
Commenti
Reply to a comment thread. Requires a Bloom/Thrive plan; rate-limited to 10/minute per company.
thread_idmessage
2 parametri facoltativi
comments_like
Commenti
Like a comment as the brand, given thread_id and comment_id (an external_id from the thread's recent_comments in comments_list). The right response to goodwill comments where a reply would feel overbearing. Only works on threads where likeable is true (Facebook Pages and LinkedIn today); otherwise suggest a reply. Never like complaints, criticism, spam, or anything offensive. Only comments from other people can be liked, not the brand's own replies. One-way: likes can't be undone through this tool, so confirm with the user before liking more than a few at once. Liking an already-liked comment is a safe no-op. Requires a plan that includes comment replies; rate-limited to 30/minute per company.
thread_idcomment_id
1 parametro facoltativo
style_learn
Voce del brand
Analyze the brand's past posts (or, for fresh accounts, brand tone) to learn tone, length, emoji/hashtag usage, and structure. Cached for a year.
style_save_feedback
Voce del brand
Save a voice/style correction after the user edits or rejects generated content, e.g. "prefers shorter captions on instagram".
feedback
2 parametri facoltativi
account_best_time
Pianificazione
Get the next available posting slot based on the brand's preferred times/days.
account_audience_best_times
Pianificazione
Best posting times per platform from the brand's own post engagement over the last 90 days (the Best time to post rule of the Reports page), each with a suggested time, a confidence level and why, falling back to the brand's saved posting times or the network's usual peak hours where its numbers are thin. start_date and end_date pick the past posts to read, not the dates to schedule. Prefer this over guessing a schedule time.
account_hashtag_groups
Pianificazione
List saved hashtag groups for a brand.
pillars_save
Pianificazione
Save the brand's content pillar mix, e.g. 40% Educational, 30% Promotional, 30% Behind-the-scenes. Percentages must sum to ~100.
pillars
1 parametro facoltativo
pillars_list
Pianificazione
Get the saved content pillar mix. Call when planning any content calendar.
templates_save
Pianificazione
Save reusable post content as a template. Use {placeholder} syntax for variables.
template_nametemplate_content
2 parametri facoltativi
templates_list
Pianificazione
List saved templates. Call before creating recurring content types.
templates_use
Pianificazione
Fill a saved template's placeholders with values to produce ready-to-post content.
template_name
2 parametri facoltativi
bio_page_get
Pagina bio
Get the brand's Bio Page, its link in bio page: settings, public_url, whether it is published and live, every block top to bottom, post_grid_profiles (the profiles a post grid can show) and the supported embed providers. Each brand has exactly one Bio Page, created automatically on first use and free on every plan. Call this before changing the page.
bio_page_update
Pagina bio
Update the Bio Page: title, bio text, slug (its address), theme color, light or dark appearance, background, profile picture, post grid columns, the social icons row, and bio_published to put it live or take it offline. Only the fields you pass change. Images must be media library urls: import them first with media_upload, media_upload_from_chat or media_direct_upload_create, or reuse a url from media_search or media_generate_ai_image. Changing bio_slug breaks the old address, so confirm with the user first. Validation errors such as a taken slug come back in errors, exactly as the dashboard shows them.
bio_blocks_create
Pagina bio
Add a block at the bottom of the Bio Page: a link button, a card (product or offer with optional image, price and button; consecutive cards can be set to a swipeable carousel), a post_grid (latest posts published through RobinReach from one profile, taken from post_grid_profiles in bio_page_get), an embed (YouTube, Vimeo, TikTok, Spotify, SoundCloud or Apple Music player) or a heading (a section label, shown as a bold title or a divider line, such as Shop or Watch). Put the content in bio_block_settings; bio_block_image_url sets a card's image. Use bio_blocks_reorder to move it.
bio_block_typebio_block_settings
2 parametri facoltativi
bio_blocks_update
Pagina bio
Change a Bio Page block's content. Only the bio_block_settings keys you pass change ("" clears one); bio_block_image_url replaces a card's image. A block's type cannot change: add a new block and delete the old one instead.
bio_block_id
3 parametri facoltativi
bio_blocks_delete
Pagina bio
Prima conferma
Permanently remove a block from the Bio Page, along with its click stats. Always confirm with the user first.
bio_block_id
1 parametro facoltativo
bio_blocks_reorder
Pagina bio
Set the order of the Bio Page blocks. Pass bio_block_ids top to bottom. Blocks you leave out keep their current order below the ones you list, so passing one id moves that block to the top.
bio_block_ids
1 parametro facoltativo
bio_page_analytics
Pagina bio
Bio Page stats, the same figures as the dashboard's Bio Page analytics: views, clicks and click-through rate on every plan; on paid plans also unique visitors, bounce rate, a daily views and clicks trend for the last 30 days, the most clicked blocks, traffic sources, countries and devices. Bot traffic is excluded. Use it to answer how the link in bio page is doing or which link gets the most clicks.
comment_automations_list
Da commento a DM
List Comment to DM automations for a brand, with every setting of each one, the social profiles that can run one (Facebook Pages and Instagram professional accounts only) and remaining plan quota. Call this before offering to create one: check can_use_comment_automation and comment_automations_remaining, and take social_profile_id from available_social_profiles. Each profile's triggers_on_all_posts says whether its automations fire on every post (always true for a Facebook Page) or only on posts published through RobinReach (an Instagram account that needs reconnecting once with Connect Via Instagram); tell the user when it is false.
comment_automations_create
Da commento a DM
Create a Comment to DM automation on one Facebook Page or Instagram professional account: people who comment get an automatic private DM. Call comment_automations_list first for a valid social_profile_id and the plan quota; the profile is fixed for the life of the automation (create a new one to target another page/account). Starts on: comment_automation_trigger_mode "keywords" (default; comment_automation_keywords then required, matched case-insensitively, single words with light stemming, multi-word phrases as an exact substring) or "any_comment" (everyone who comments). Timing: right away, or comment_automation_delay_minutes later. What they get: comment_automation_dm_message as plain text (comment_automation_button_style "none"), with one link button ("link"), or with a tap button that sends the link after the tap ("tap"); "link" and "tap" need comment_automation_button_url, and every button text has a default. Only "tap" can check that the person follows the account before the link goes out (comment_automation_require_follow, Instagram only) or send one reminder to people who got the link but didn't open it (comment_automation_follow_up_enabled); a "link" automation that asks for either is switched to "tap" automatically, as in the dashboard, and the response's note says so. Optional public reply under the comment (comment_automation_send_public_reply, which requires comment_automation_public_reply_message). Each person is only ever DM'd once per automation, even if they comment again later or while a delayed DM is waiting: deliberate spam prevention, not a bug. Facebook fires on top-level comments on any Page post. Instagram fires on every comment, replies included, on every post when the profile's triggers_on_all_posts (from comment_automations_list) is true, and otherwise only on posts published through RobinReach until the account is reconnected.
social_profile_idcomment_automation_namecomment_automation_dm_message
17 parametri facoltativi
comment_automations_update
Da commento a DM
Change any setting of an existing Comment to DM automation: name, trigger mode and keywords, delay, DM message, button style, link and button texts, follower check and its message, reminder with its message and timing, public reply, and whether it is active. Pass only what changes; everything else stays as it is. The same rules as comment_automations_create apply: the follower check (Instagram only) and the reminder need the "tap" style, and a "link" automation is switched to it automatically when either is turned on. The social profile it's attached to cannot be changed; create a new automation instead.
comment_automation_id
20 parametri facoltativi
comment_automations_delete
Da commento a DM
Prima conferma
Permanently delete a Comment to DM automation. Always confirm with the user first.
comment_automation_id
1 parametro facoltativo
comment_automations_toggle_active
Da commento a DM
Pause or resume a Comment to DM automation without changing its settings.
comment_automation_id
1 parametro facoltativo
rss_list
Feed RSS
List all RSS feeds for the brand.
rss_validate
Feed RSS
Validate RSS feed parameters. Always call before rss_create or rss_update; never call those without a preceding successful rss_validate.
rss_create
Feed RSS
Create an RSS feed. Call rss_validate first. rss_publish_immediately and rss_auto_schedule are mutually exclusive.
rss_feed_namerss_feed_url
13 parametri facoltativi
rss_update
Feed RSS
Update an existing RSS feed. Call rss_validate first.
rss_feed_id
15 parametri facoltativi
rss_delete
Feed RSS
Prima conferma
Permanently delete an RSS feed (does not delete posts it already created). Always confirm with the user first.
rss_feed_id
1 parametro facoltativo
rss_toggle_pause
Feed RSS
Pause or resume an RSS feed. Resuming checks the feed for new items right away and restarts its schedule.
rss_feed_id
1 parametro facoltativo
rss_sync
Feed RSS
Manually trigger an RSS feed sync now.
rss_feed_id
1 parametro facoltativo
repurposing_list
Riadatta e importa
List repurposing tasks and the available_source_profiles, the only profiles valid as a source. Any connected profile can be a destination.
repurposing_create
Riadatta e importa
Create a task that repurposes content from one source profile to one or more destination profiles. Call repurposing_list first; only offer source profiles from its available_source_profiles list.
source_profile_iddestination_profile_ids
6 parametri facoltativi
repurposing_update
Riadatta e importa
Update a repurposing task's source, destinations, or settings.
repurposing_task_id
8 parametri facoltativi
repurposing_delete
Riadatta e importa
Prima conferma
Permanently delete a repurposing task. Always confirm with the user first.
repurposing_task_id
1 parametro facoltativo
repurposing_toggle_pause
Riadatta e importa
Pause or resume a repurposing task.
repurposing_task_id
1 parametro facoltativo
repurposing_run
Riadatta e importa
Run a repurposing task now. Returns how many posts it created, or why nothing could be fetched from the source (for example an expired connection).
repurposing_task_id
1 parametro facoltativo
content_article_to_posts
Riadatta e importa
Convert an article URL into draft posts, optionally tagged with custom hashtags.
article_url
4 parametri facoltativi
store_sync_products
Riadatta e importa
Sync products from a connected Shopify/Etsy/WooCommerce store into new draft posts. Pass store_type: "auto" to detect automatically.
connect_links_list
Link per i clienti
List Connect Links for this brand: client-facing onboarding links that let a client connect their own social profiles without an account.
connect_links_create
Link per i clienti
Prima conferma
Create a Connect Link and return its one-time plaintext URL. Gated by the brand's plan limit. Confirm with the user first; the URL is shown only once and cannot be retrieved again through this tool.
link_title
3 parametri facoltativi
approval_links_list
Link per i clienti
List Approval Links for this brand: client-facing links that let a client review and approve/reject pending posts without an account. Only available on Thrive and Scale plans.
approval_links_create
Link per i clienti
Prima conferma
Create an Approval Link and return its one-time plaintext URL. Only available on Thrive and Scale plans. Confirm with the user first; the URL is shown only once and cannot be retrieved again through this tool.
link_title
4 parametri facoltativi
account_status
Account e social
Get plan limits/usage, brand settings, connected profiles, voice preferences, and writing style. Call once at the start of a session.
account_brands
Account e social
List every brand on this account with profile/post counts. Use when the account has multiple brands and you need to ask the user which to work in.
account_profiles
Account e social
List connected social profiles for a brand, with per-platform character limits. requires_media: true means the profile rejects a post with no image or video.
account_locations
Account e social
List the locations this brand can tag on Instagram and Facebook posts: its connected Facebook Pages that have an address. Each says whether Instagram can use it (instagram: true needs a map pin on the Page). Pass page_id as platform_options.instagram.location_id and/or platform_options.facebook.place_id.
pinterest_list_boards
Account e social
List Pinterest boards for a connected profile.
youtube_list_playlists
Account e social
List YouTube playlists for a connected profile.
wordpress_list_categories
Account e social
List WordPress categories. Never guess category IDs; call this first.
wordpress_list_tags
Account e social
List WordPress tags. Never guess tag IDs; call this first.
Nessuno strumento corrisponde a questa ricerca.
Nomi e descrizioni sono mostrati esattamente come li invia il server, in inglese.
La maggior parte dei post AI venuti male nasce da tentativi alla cieca. Il server è fatto per eliminarli.
posts_validate controlla contenuto, media e limiti di ogni social. posts_create ripete gli stessi controlli sul server, così un passaggio saltato non passa mai.
Bacheche, playlist, categorie e tag di WordPress arrivano da strumenti di elenco, e le istruzioni dicono al modello di non indovinarne mai uno.
posts_bulk_create accetta fino a 20 post. Ognuno viene controllato a parte e gli errori tornano con il loro indice, così un post sbagliato non trascina mai gli altri.
URL pubblici, file allegati nella chat e caricamenti diretti firmati per i file locali. media_view permette al modello di vedere fino a 10 immagini prima di scriverne.
Ogni errore JSON-RPC riporta l'id della richiesta, gli errori degli strumenti arrivano con isError e quelli imprevisti hanno un id di richiesta da citare all'assistenza.
9 strumenti pubblicano subito, eliminano per sempre o restituiscono un link mostrato una sola volta. Le loro descrizioni e le istruzioni del server dicono al modello di chiedere prima conferma alla persona.
Snippet per i client più comuni. Claude e ChatGPT accedono a RobinReach, quindi la loro configurazione non contiene chiavi. La tua dashboard ha gli altri con la tua chiave già inserita.
claude mcp add --transport http robinreach https://robinreach.com/mcp/v1/messages
Aggiunge RobinReach a Claude Code via HTTP, senza chiave nell'URL. Poi esegui /mcp in Claude Code, seleziona robinreach e scegli Authenticate: il browser apre RobinReach, dove accedi e scegli tutto l'account o un solo brand. Niente browser? Usa invece l'URL con chiave API della tua dashboard.
codex mcp add robinreach -- npx -y mcp-remote "https://robinreach.com/mcp/v1/messages?api_key=YOUR_API_KEY"
Codex si collega tramite il ponte mcp-remote, che richiede Node.js.
gemini mcp add --transport http robinreach "https://robinreach.com/mcp/v1/messages?api_key=YOUR_API_KEY"
Aggiunge RobinReach a Gemini CLI via HTTP.
{
"mcpServers": {
"robinreach": {
"url": "https://robinreach.com/mcp/v1/messages?api_key=YOUR_API_KEY"
}
}
}
Apri Cursor Settings, poi MCP & Integrations, poi New MCP Server, e aggiungi questo blocco.
{
"servers": {
"robinreach": {
"type": "http",
"url": "https://robinreach.com/mcp/v1/messages?api_key=YOUR_API_KEY"
}
}
}
Salvalo nel tuo workspace, oppure esegui MCP: Add Server dalla palette dei comandi e scegli HTTP. Usalo con Copilot Chat in modalità Agent.
{
"mcpServers": {
"robinreach": {
"serverUrl": "https://robinreach.com/mcp/v1/messages?api_key=YOUR_API_KEY"
}
}
}
In Windsurf apri Settings, poi Cascade, poi Manage MCPs e View raw config.
https://robinreach.com/mcp/v1/messages
Nessun file di configurazione e niente Node.js. In Claude sul web o in Claude Desktop apri Settings, poi Connectors, clicca su Add custom connector, chiamalo RobinReach e incolla questo URL. Poi clicca su Connect, accedi a RobinReach e scegli tutto l'account o un solo brand.
https://robinreach.com/mcp/v1/messages
App per ChatGPT in arrivo. Nel frattempo collegalo in Developer mode con un piano ChatGPT a pagamento: apri Settings, poi Apps & Connectors, poi Advanced settings, e attiva Developer mode. Torna in Apps & Connectors, clicca su Create, chiamalo RobinReach, incolla questo URL, imposta Authentication su OAuth e crealo. Poi clicca su Connect e accedi. Le app in Developer mode sono disattivate di default, quindi attiva RobinReach dal menu + in ogni nuova chat.
import anthropic client = anthropic.Anthropic() response = client.beta.messages.create( model="claude-opus-5-5", max_tokens=16000, betas=["mcp-client-2025-11-20"], mcp_servers=[{ "type": "url", "url": "https://robinreach.com/mcp/v1/messages", "name": "robinreach", "authorization_token": "YOUR_API_KEY", }], tools=[{"type": "mcp_toolset", "mcp_server_name": "robinreach"}], messages=[{"role": "user", "content": "What is scheduled for next week?"}], )
Usa RobinReach dal tuo codice con il connettore MCP della Claude API. Claude chiama gli strumenti per te, e la chiave viaggia come token Bearer.
from openai import OpenAI client = OpenAI() response = client.responses.create( model="gpt-5", tools=[{ "type": "mcp", "server_label": "robinreach", "server_url": "https://robinreach.com/mcp/v1/messages", "headers": {"Authorization": "Bearer YOUR_API_KEY"}, }], input="What is scheduled for next week?", )
La OpenAI Responses API si collega ai server MCP remoti allo stesso modo. Passa la chiave nell'header Authorization.
curl -s https://robinreach.com/mcp/v1/messages \ -H "Authorization: Bearer YOUR_API_KEY" \ -H "Content-Type: application/json" \ -d '{"jsonrpc":"2.0","id":1,"method":"tools/list"}'
Il protocollo puro. Sostituisci tools/list con tools/call e un name e degli arguments per eseguire uno strumento.
YOUR_API_KEY è un segnaposto per i client che usano una chiave API. Genera una chiave in Integrazioni, nella tua dashboard. Claude e ChatGPT invece accedono con il login e non hanno bisogno di chiavi.
Lo skill di RobinReach dà a Claude quello che gli strumenti da soli non possono dare: come si comporta ogni social, come pianificare un calendario e come scrivere con la tua voce.
curl -fsSL "https://robinreach.com/downloads/robinreach-claude-skill.zip?v=0dbca3b6" -o /tmp/rr-skill.zip && mkdir -p ~/.claude/skills && unzip -oq /tmp/rr-skill.zip -d ~/.claude/skills && rm /tmp/rr-skill.zip && echo "RobinReach skill installed."
Incolla l'URL, accedi o aggiungi una chiave e il tuo agente può gestire 13 social.
L'accesso MCP è incluso in Bloom, Thrive e Scale.