Affinda MCP

Live

API KEY

AI

Files & Documents

Affinda MCP turns documents into structured data: extract and validate invoices, resumes, and contracts from your agent.

  • Per-user credentials: each call uses the actual user's token, never a shared bot.
  • Encrypted per-tenant vault: AES-256, resolved at request time, never in LLM context.
  • Scoped before every call: pre-call scope check, 90-day SIEM-exportable audit chain.
Affinda MCP
agent · Acme Q3
Run
Add Connection To Integration in Affinda MCP
S
affindamcp_add_connection_to_integration
85ms
Affinda MCP agent
Attach an existing service connection to an integration..
Sources: Affinda MCP
affindamcpmcp
1 tool call
18:29
Message Claude...

Tools your agent reaches for on Affinda, scoped per user.

CALL ANY TOOL
Upload, extract, validate, and integrate structured data from invoices, resumes, and contracts.
affindamcp_add_connection_to_integration
Add connection to integration
Attach an existing service connection to an integration.
Parameters
Name
Type
Required
Description
connection_id
string
Required
No description.
integration_id
string
Required
No description.
affindamcp_archive_documents
Archive documents
affindamcp_assign_document_type_to_workspace
Assign document type to workspace
affindamcp_bulk_create_data_source_values
Bulk create data source values
affindamcp_create_api_token
Create api token
affindamcp_create_data_source_value
Create data source value
affindamcp_create_field
Create field
affindamcp_create_matching_criterion
Create matching criterion
affindamcp_create_validation_rule
Create validation rule
affindamcp_delete_data_source
Delete data source
affindamcp_delete_field
Delete field
affindamcp_delete_integration_secret
Delete integration secret
affindamcp_get_data_source
Get data source
affindamcp_get_document_extraction
Get document extraction
affindamcp_get_field
Get field
affindamcp_get_integration
Get integration
affindamcp_get_validation_rule
Get validation rule
affindamcp_list_data_source_values
List data source values
affindamcp_list_document_types
List document types
affindamcp_list_integration_runs
List integration runs
affindamcp_list_integrations
List integrations
affindamcp_list_pipedream_apps
List pipedream apps
affindamcp_populate_document_type_fields
Populate document type fields
affindamcp_remove_connection_from_integration
Remove connection from integration
affindamcp_revert_integration_version
Revert integration version
affindamcp_run_integration
Run integration
affindamcp_set_integration_secret
Set integration secret
affindamcp_update_data_source
Update data source
affindamcp_update_field
Update field
affindamcp_update_organization
Update organization

For more tools, view docs.

Build your Agent
Same auth pattern across LangChain, OpenAI, Anthropic, and Google ADK.
Python · LlamaIndex
from langchain_mcp_adapters.client import MultiServerMCPClient
from scalekit import ScalekitClient

client = ScalekitClient(env_url=ENV_URL, client_id=CLIENT_ID, client_secret=SECRET)
token = client.agent.get_token(user_id="user_id", connector="affindamcp")

mcp = MultiServerMCPClient({
"affindamcp": {
"url": "https://mcp.scalekit.com/affindamcp",
"headers": {"Authorization": "Bearer " + token}
}
})
tools = await mcp.get_tools()
import OpenAI from "openai";
import { ScalekitClient } from "@scalekit-sdk/node";

const client = new ScalekitClient({ envUrl, clientId, clientSecret });
const token = await client.agent.getToken({ userId: "user_id", connector: "affindamcp" });

const openai = new OpenAI();
// Connect to MCP at https://mcp.scalekit.com/affindamcp
// Pass: Authorization: Bearer + token
import Anthropic from "@anthropic-ai/sdk";
import { ScalekitClient } from "@scalekit-sdk/node";

const client = new ScalekitClient({ envUrl, clientId, clientSecret });
const token = await client.agent.getToken({ userId: "user_id", connector: "affindamcp" });

const anthropic = new Anthropic();
// Connect to MCP at https://mcp.scalekit.com/affindamcp
// Pass: Authorization: Bearer + token
from google.adk.agents import LlmAgent
from scalekit import ScalekitClient

client = ScalekitClient(env_url=ENV_URL, client_id=CLIENT_ID, client_secret=SECRET)
token = client.agent.get_token(user_id="user_id", connector="affindamcp")
# Connect to MCP at https://mcp.scalekit.com/affindamcp
# Pass: Authorization: Bearer + token
Try these prompts
Copy any prompt into your agent. Each maps directly to a Affinda tool. Click to copy, paste into your agent, done.
Get started
Copy the prompt
Copied
Block until every document in a workspace has finished processing?
Copy the prompt
Copied
Update one or more settings on an existing workspace?
Advanced
Copy the prompt
Copied
Verify a service connection’s credentials are still valid?
Copy the prompt
Copied
Create or update a secret on an integration?
SEE HOW AUTH WORKS
Your users connect once. Their Affinda credentials stay vaulted, every call is scope-checked, and every action is logged.
1
Authorize
Your user connects
Affinda MCP
once. We tie it to their identity and the meetings they approved — no shared bot account, no org-wide access
Who:
user ‘A’
when:
Once per user
access:
Limited to user
2
Store
Their
Affinda MCP
token lives in a vault scoped to them. User A's meetings are never reachable by an agent acting for user B, even on the same connection
vault:
encrypted
scope:
per-user
tokens:
auto-refreshed
3
Resolve
When your agent calls a
Affinda MCP
tool, we fetch the right token server-side. It never touches your agent, never appears in the LLM context, never shows up in your logs
speed:
~40ms
check:
before every call
seen by:
nobody
4
Audit
Every
Affinda MCP
tool call is logged — who triggered it, which meeting was fetched, what came back. 90 days of history, tied to the user who authorized it
history:
90 days
export:
SIEM-ready
logged:
every call
Test other agents
See the same per-user auth pattern across other connectors.
GTM and RevOps Teams
Deal room sync
Pulls opportunity context from Salesforce, captures key decisions from Slack, and syncs a running summary to the deal room doc in Google Drive, but only when the deal actually changed.
People Ops and HR teams
Performance review collector
Collects review feedback from Airtable and Google Forms scoped to each manager's direct reports, writes per-employee summaries to Notion, and DMs the manager a Slack digest.
People Ops and HR teams
Offer letter routing agent
Drafts the offer in PandaDoc, blocks on the hiring manager's approval in Slack, then emails the candidate their e-signature link. Every call runs as the recruiter who triggered it, never a shared HR bot.
Support and Ops Teams
Support ticket automation agent
Fetches new Zendesk tickets, drafts a reply from Notion knowledge base articles, digests what it cannot answer to Slack, and archives the rest, acting as the support agent rather than a shared API key.
Test other agents
See the same per-user auth pattern across other connectors.
GTM
Deal room sync agent
Pull opportunity context from Salesforce, capture decisions from Slack, and keep the Google Drive deal room doc current.
PEOPLE OPS
Performance review collector agent
Collect review feedback from Airtable and Google Forms per manager, summarise each report in Notion, and DM the digest in Slack.
PEOPLE OPS
Offer letter routing agent
Draft the offer in PandaDoc, gate it on hiring manager approval in Slack, then email the candidate their signature link.
SUPPORT
Support ticket automation (Google ADK)
Fetch, annotate, and archive Zendesk tickets with Notion context, digesting anything it cannot answer to Slack.
Why Scalekit
Secure your agent's access. Connectors ship in minutes
01.
Shared tokens break per-user analytics
A shared token looks fine in a demo. In production every call looks like a service account. Scalekit resolves the real user credential.
// shared token
audit → bot_service_account

// scalekit
audit → user_abc ✓
02.
Authentication is not authorization
03.
Multi-tenancy is architectural
04.
One connector today. Ten tomorrow.
“Our agents act across Salesforce, Gong, Google Drive, and more, on behalf of every customer. Scalekit behind the scenes meant we can keep adding tools without ever rebuilding how credentials or tool calling work.”
Venu Madhav Kattagoni
Head of Engineering / Von
FAQs
Frequently Asked Questions

Does the agent access Affinda as the user or as a shared key?
As the user. Each workspace member authorizes once and Scalekit resolves their credential at request time. Audit logs attribute every action to that user, not a shared service account.

Where is the Affinda API key stored?
In Scalekit's managed AES-256 token vault, namespaced per tenant. Refresh is automatic. Revocation is a single dashboard action. Tokens never appear in prompts, logs, or LLM context.

Can I limit what the agent is allowed to do in Affinda?
Yes. Pass a tool name filter to listScopedTools so the document agent only sees the subset you authorize. Pre-API-call scope checks block out-of-policy actions before the request reaches Affinda.

What happens when a user revokes Affinda access?
The connection is invalidated on the next tool call. Subsequent requests for that user fail closed with a clear error. Other users in the tenant remain unaffected. The event is logged for audit.

Where do parsed documents and extracted data live?
In the authorizing user's Affinda workspace. Uploads, extractions, and validations follow workspace membership, so invoices and resumes never cross tenant boundaries.

Start in your coding agent
Up and running in one command
Install the Scalekit skill in your editor of choice. Connector, auth, tools, prompt, all wired up
Claude Code REPL
/plugin marketplace add scalekit-inc/claude-code-authstack
/plugin install agentkit@scalekit-auth-stack
Cursor Code REPL
# ~/.cursor/mcp.json
{
""mcpServers"": {
""affindamcp"": {
""url"": ""https://mcp.scalekit.com/affindamcp"",
""headers"": { ""Authorization"": ""Bearer $SCALEKIT_TOKEN"" }
}
}
}
Codex Code REPL
# ~/.codex/config.toml
[mcp_servers.affindamcp]
url = ""https://mcp.scalekit.com/affindamcp""
auth_env = ""SCALEKIT_TOKEN""
Copilot Code REPL
# .vscode/mcp.json
{
""servers"": {
""affindamcp"": {
""url"": ""https://mcp.scalekit.com/affindamcp"",
""type"": ""http""
}
}
}