Felt MCP

Live

OAUTH 2.1

GEOSPATIAL

Analytics

Felt holds the maps, layers, and spatial data your team reasons about together. Felt MCP gives your agent authenticated access scoped to the user who authorized it.

  • Acts as the user: access and write actions stay tied to the Felt account that authorized the agent.
  • Credentials stay vaulted: AES-256, resolved at request time, never in LLM context.
  • Scoped before every call: permissions enforced. 90-day audit trail.
Felt MCP
agent · Acme Q3
Run
Which service areas overlap the new territory?
S
felt_map_layers_list
137ms
Felt agent
3 of 11 service-area polygons intersect the new territory, covering roughly 40% of its area.
Sources: 1 map, 11 layers
feltmcp
4 calls
18:29
Message Claude...

Tools your geospatial agent reaches for on Felt MCP, scoped per user.

CALL ANY TOOL
Geospatial work on Felt: create and update maps, manage layers and elements, query connected spatial databases, and share map links.
feltmcp_add_data_source_table_to_map
Add data source table to map
Add a data source table to the map as a new layer.
Parameters
Name
Type
Required
Description
map_id
string
Required
The ID of the map.
table_id
string
Required
The table ID to add
caption
string
Optional
Optional; default to omitting. Add a caption only when the layer name is opaque: agency acronyms, GIS jargon, or obscure dataset names a layperson can't decode (e.g. 'NHD Flowlines', 'CALVEG Vegetation Types'). Do NOT add a caption that rephrases the name with synonyms (e.g. 'Wind Farms' → 'Major wind energy installations') or pads it with filler qualifiers like 'Active', 'Major', or 'Historical': if the caption doesn't tell the reader something the name alone didn't, omit it. Also add a caption when the styling encodes a data attribute: color or size by a column: to tell the reader what the symbology represents (e.g. 'Colored by median household income', 'Sized by 2020 population'). If both apply (opaque name AND attribute encoding), combine them concisely (e.g. 'NHD flowlines, colored by stream order').
feltmcp_browse_data_source_tables
Browse data source tables
feltmcp_browse_felt_library
Browse felt library
feltmcp_browse_felt_server
Browse felt server
feltmcp_create_layer_from_data_source
Create layer from data source
feltmcp_create_layer_from_felt_layers
Create layer from felt layers
feltmcp_delete_annotation
Delete annotation
feltmcp_delete_layer
Delete layer
feltmcp_generate_fsl
Generate fsl
feltmcp_get_layer_group_properties
Get layer group properties
feltmcp_get_layer_properties
Get layer properties
feltmcp_get_map_layers
Get map layers
feltmcp_get_project
Get project
feltmcp_get_tabular_data_from_data_source
Get tabular data from data source
feltmcp_help_center
Help center
feltmcp_inspect_data_source_table_columns
Inspect data source table columns
feltmcp_inspect_layer
Inspect layer
feltmcp_list_annotations
List annotations
feltmcp_list_data_sources
List data sources
feltmcp_list_maps
List maps
feltmcp_poll_layer_processing_status
Poll layer processing status
feltmcp_prepare_file_upload
Upload prepare file
feltmcp_refresh_data_source_layer
Refresh data source layer
feltmcp_render_map
Render map
feltmcp_set_layer_group_interaction
Set layer group interaction
feltmcp_share_map
Share map
feltmcp_update_layer_group_properties
Update layer group properties
feltmcp_update_layer_properties
Update layer properties
feltmcp_upload_contents_to_map
Upload contents to map
feltmcp_upsert_annotations
Upsert annotations

For more tools, view docs.

Build your Agent
Drop the toolkit in, point it at the user, and your geospatial agent can use Felt from the first run.
Python · LlamaIndex
import { ScalekitClient } from "@scalekit-sdk/node";
import { createReactAgent } from "@langchain/langgraph/prebuilt";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);

// Felt MCP tools, scoped to the signed-in user
const { tools } = await sk.tools.listScopedTools("user_123", {
filter: { connectionNames: ["feltmcp"], toolNames: [
"feltmcp_add_data_source_table_to_map",
"feltmcp_browse_data_source_tables",
"feltmcp_browse_felt_library"
] },
pageSize: 100,
});

const agent = createReactAgent({ llm, tools });
await agent.invoke({ messages: [{ role: "user", content: "Which service areas overlap the new territory?" }] });
import OpenAI from "openai";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);

// Felt MCP tools, scoped to the signed-in user
const { tools } = await sk.tools.listScopedTools("user_123", {
filter: { connectionNames: ["feltmcp"], toolNames: [
"feltmcp_add_data_source_table_to_map",
"feltmcp_browse_data_source_tables",
"feltmcp_browse_felt_library"
] },
pageSize: 100,
});

const openai = new OpenAI();
const res = await openai.responses.create({
model: "gpt-5",
tools: tools.map((t) => t.openai),
input: "Which service areas overlap the new territory?",
});
import Anthropic from "@anthropic-ai/sdk";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);

// Felt MCP tools, scoped to the signed-in user
const { tools } = await sk.tools.listScopedTools("user_123", {
filter: { connectionNames: ["feltmcp"], toolNames: [
"feltmcp_add_data_source_table_to_map",
"feltmcp_browse_data_source_tables",
"feltmcp_browse_felt_library"
] },
pageSize: 100,
});

const anthropic = new Anthropic();
const msg = await anthropic.messages.create({
model: "claude-opus-4-6",
max_tokens: 1024,
tools: tools.map((t) => t.anthropic),
messages: [{ role: "user", content: "Which service areas overlap the new territory?" }],
});
import { Agent } from "@google/adk/agents";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);

// Felt MCP tools, scoped to the signed-in user
const { tools } = await sk.tools.listScopedTools("user_123", {
filter: { connectionNames: ["feltmcp"], toolNames: [
"feltmcp_add_data_source_table_to_map",
"feltmcp_browse_data_source_tables",
"feltmcp_browse_felt_library"
] },
pageSize: 100,
});

const agent = new Agent({
name: "feltmcp_agent",
model: "gemini-2.5-pro",
instruction: "Act as the geospatial agent for the signed-in user.",
tools,
});
await agent.run("Which service areas overlap the new territory?");
Try these prompts
Paste any prompt into your agent to start using Felt.
Map review
Copy the prompt
Copied
Which service areas overlap the new territory?
Copy the prompt
Copied
List the layers on the coverage map and their sources.
Copy the prompt
Copied
Show maps updated in the last week.
Editing
Copy the prompt
Copied
Create a map for Q4 territory planning.
Copy the prompt
Copied
Upload this GeoJSON as a layer on the coverage map.
Copy the prompt
Copied
Add a note element on the map marking the new depot.
Spatial queries
Copy the prompt
Copied
Query the connected database for sites within 5km of the depot.
Copy the prompt
Copied
Count customers per service area polygon.
Copy the prompt
Copied
Which layers have no data rows?
SEE HOW AUTH WORKS
Users authorize Felt once. Their credentials stay vaulted, every call is checked, and every action is logged.
1
Authorize
Your user connects
Felt 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
Felt 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
Felt 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
Felt 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
Same per-user auth pattern across other agents and MCP connectors. Working code, live demos, fork what fits.
GTM and RevOps Teams
Revenue forecast commentary
Pulls open pipeline from Salesforce and HubSpot, calculates coverage against quota, flags at-risk stages, posts commentary to Slack, and logs every snapshot to Google Sheets.
GTM and RevOps Teams
Deal intelligence agent
Pulls recent Gong calls, scores deal risk with an LLM, cross-references the record in Attio, and DMs each owner their at-risk deals in Slack. Every read is scoped to that rep's own access.
Engineering Teams
Engineering standup agent
Pulls commits from GitHub and GitLab, tracks issue movement in Jira, and posts a per-engineer standup brief to Slack. Each engineer's activity is read on their own delegated OAuth.
GTM and RevOps Teams
Competitive intelligence briefing agent
Scans Gong calls for competitor mentions, matches each one to its Notion battlecard, and DMs every affected rep a single Slack digest per cycle. Every call runs as the PMM who owns the briefing, never a shared bot.
Test other agents
Same per-user auth pattern across other agents and MCP connectors. Working code, live demos, fork what fits.
SALES
Deal intelligence agent
Score Gong call risk with an LLM, cross-reference the Attio record, and DM each owner their at-risk deals in Slack.
ENGINEERING
Engineering standup agent
Pull commits from GitHub and GitLab, track Jira issue movement, and post a per-engineer standup brief to Slack.
GTM
Revenue forecast agent
Score pipeline coverage against quota across Salesforce and HubSpot, post forecast commentary to Slack, log snapshots to Sheets.
GTM
Competitive intelligence briefing agent
Scan Gong calls for competitor mentions, match each one to its Notion battlecard, and DM every affected rep a single Slack digest.
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 so attribution, audit, and scope stay accurate.
// shared token
audit → bot_service_account
user_filter → broken

// scalekit
audit → user_abc
scope → enforced ✓
02.
Authentication is not authorization
03.
Multi-tenancy is architectural
04.
Felt today. Others 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 Felt as the user or as a shared key?
As the user. Each 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 Felt oauth 2.1 credential stored?
In Scalekit's managed AES-256 token vault, namespaced per tenant. Refresh is automatic. Revocation is a single dashboard action. Credentials never appear in prompts, logs, or LLM context.
Can I limit what the agent is allowed to do in Felt?
Yes. Pass a tool name filter to listScopedTools so the geospatial agent only sees the subset you authorize. Pre-API-call scope checks block out-of-policy actions before the request reaches Felt.
What happens when a user revokes Felt 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.
Can the agent edit maps the user only has view access to?
No. Felt enforces per-map roles, and the connector calls as the authorizing user, so a viewer's agent can read but not write. Attempted edits fail closed with a clear error and the attempt is logged.
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"": {
""feltmcp"": {
""url"": ""https://mcp.scalekit.com/feltmcp"",
""headers"": { ""Authorization"": ""Bearer $SCALEKIT_TOKEN"" }
}
}
}
Codex Code REPL
# ~/.codex/config.toml
[mcp_servers.feltmcp]
url = ""https://mcp.scalekit.com/feltmcp""
auth_env = ""SCALEKIT_TOKEN""
Copilot Code REPL
# .vscode/mcp.json
{
""servers"": {
""feltmcp"": {
""url"": ""https://mcp.scalekit.com/feltmcp"",
""type"": ""http""
}
}
}