Mireye MCP server for AI agents

Live

API KEY

LOCATION DATA

AI

Mireye gives your agent US location data: geocode addresses, fetch public data fields for a point, enrich and search parcels, measure drive-time proximity and labor shed, and ask cited questions about a site.

  • Per-user credentials: each call uses the actual user's API key, 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.
Mireye
agent · Acme Q3
Run
What is the nearest substation to 1200 Industrial Way in Reno?
S
mireye_proximity_nearest
148ms
Site selection agent
The nearest substation is an 8 minute drive from that address. The closest airport is 14 minutes away.
Sources: 1 site, 2 infrastructure types
mireye
2 results
18:29
Message Claude...

Tools your location data agent reaches for on Mireye, scoped per user.

CALL ANY TOOL
21 tools for location data in Mireye: geocode addresses, fetch public data fields, enrich and search parcels, measure proximity and labor shed, and ask cited questions about sites.
mireye_address_geocode
Address geocode
Resolve a US street address to a coordinate and report how precise that coordinate is. Returns lat, lng, accuracy, accuracy_type (rooftop, or range_interpolation, which can be off by about 2.9 km in rural areas), match_type, normalized_address, provider, source, parcel_grade and precision_note. Use mireye_address_geocode to check or reuse a coordinate before calling other tools with lat and lng. mireye_location_fetch, mireye_location_ask and mireye_parcel_enrich also accept an address directly and return the same geocode block. Free.
Parameters
Name
Type
Required
Description
address
string
Required
A full US street address to turn into a coordinate, 1 to 256 characters, with house number, street, city and state or ZIP. A bare street with no locality, or an address the geocoder can only place at a ZIP, city or county centroid, is rejected with 404 address_too_coarse. Example: 350 5th Ave, New York, NY 10118.
mireye_enrich_fields_list
List enrich fields
mireye_fetch_fields_list
List fetch fields
mireye_field_request_create
Create field request
mireye_field_request_get
Get field request
mireye_location_ask
Location ask
mireye_location_fetch
Fetch location
mireye_operation_get
Get operation
mireye_parcel_enrich
Parcel enrich
mireye_parcels_search
Search parcels
mireye_plans_list
List plans
mireye_proximity_distance
Proximity distance
mireye_proximity_labor_shed
Proximity labor shed
mireye_proximity_nearest
Proximity nearest
mireye_proximity_screen
Proximity screen
mireye_run_create
Create run
mireye_run_get
Get run
mireye_search_fields_list
List search fields
mireye_site_ask
Site ask
mireye_site_create
Create site
mireye_site_get
Get site
Build your Agent
Same auth pattern across LangChain, OpenAI, Anthropic, and Google ADK.
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);

// Mireye tools scoped to this user
const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["mireye"], toolNames: [
    "mireye_address_geocode",
    "mireye_proximity_nearest",
    "mireye_parcel_enrich"] },
  pageSize: 100,
});

const agent = createReactAgent({ llm, tools });
await agent.invoke({ messages: [{ role: "user", content: "Geocode 1200 Industrial Way in Reno, find the nearest substation, and pull the parcel owner and zoning" }] });
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);
const openai = new OpenAI();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["mireye"] }, pageSize: 100,
});

const res = await openai.chat.completions.create({
  model: "gpt-5",
  messages: [{ role: "user", content: "Geocode 1200 Industrial Way in Reno, find the nearest substation, and pull the parcel owner and zoning" }],
  tools,
});

// Execute the tool call with the user's vaulted Mireye API key
await sk.tools.executeTool(res.choices[0].message.tool_calls[0], "user_123");
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);
const anthropic = new Anthropic();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["mireye"] }, pageSize: 100,
});

const msg = await anthropic.messages.create({
  model: "claude-sonnet-5",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Geocode 1200 Industrial Way in Reno, find the nearest substation, and pull the parcel owner and zoning" }],
  tools,
});

// Tool call runs with the user's vaulted Mireye API key
await sk.tools.executeTool(msg.content, "user_123");
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);

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["mireye"] }, pageSize: 100,
});

const agent = new Agent({
  name: "location_data_agent",
  model: "gemini-2.5-pro",
  instruction: "Mireye tools scoped to this user",
  tools,
});

await agent.run("Geocode 1200 Industrial Way in Reno, find the nearest substation, and pull the parcel owner and zoning");
Try these prompts
Copy any prompt into your agent. Each maps directly to a Mireye tool. Click to copy, paste into your agent, done.
Locations
Copy the prompt
Copied
Geocode 1200 Industrial Way, Reno, NV and tell me how precise the match is.
Copy the prompt
Copied
Fetch the flood zone and elevation for this address.
Copy the prompt
Copied
Ask whether this address sits near wetlands.
Parcels
Copy the prompt
Copied
Enrich this address with the parcel owner, zoning, and assessed value.
Copy the prompt
Copied
Find parcels in Washoe County over 50 acres zoned industrial.
Copy the prompt
Copied
List the fields I can request when enriching a parcel.
Proximity and sites
Copy the prompt
Copied
Find the nearest substations and airports to this site.
Copy the prompt
Copied
Estimate the labor force within a 45 minute drive of this site.
Copy the prompt
Copied
Screen these 30 candidate sites to those within 45 minutes of our distribution hub.
SEE HOW AUTH WORKS
Each user connects their own Mireye API key once, and Scalekit sends it with every call. Keys stay vaulted, every call is scope checked, and every action is logged.
1
Authorize
Your user connects
Mireye
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
Mireye
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
Mireye
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
Mireye
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 search and analytics connectors.
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.
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.
Test other agents
See the same per-user auth pattern across other search and analytics connectors.
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.
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.
Why Scalekit
Secure your agent's access. Connectors ship in minutes
01.
Shared tokens break per-user analytics
A shared Mireye API key looks fine in a demo. In production every parcel enrichment and site run looks like one service account, and you cannot tell which user triggered it. Scalekit resolves the credential of the actual user who triggered the agent, never a shared bot.
// shared key
audit → bot_service_account

// scalekit
audit → user_abc ✓
02.
Authentication is not authorization
03.
Multi-tenancy is architectural
04.
Mireye today. Ten connectors 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 Mireye as the user or through a shared key?
As the user. Each user connects their own Mireye API key once, and Scalekit sends it with every call. Audit logs attribute every parcel lookup and run to that user, not a shared service account.
Where is the Mireye API key stored?
In Scalekit's managed AES-256 token vault, namespaced per tenant. To rotate it, the user reconnects with a new API key. Revocation is a single dashboard action. Credentials never appear in prompts, logs, or LLM context.
Can I limit what the agent does in Mireye?
Yes. Filter by tool name in listScopedTools to expose only what you want, for example the free fetch and geocode tools without mireye_parcel_enrich or mireye_parcels_search, which carry per-plan pricing in the docs. Scalekit also enforces scope checks before every API call.
What happens when a user revokes Mireye 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.
Which locations does Mireye cover?
Geocoding, parcel, fetch, and labor shed tools work on US locations. mireye_proximity_distance, mireye_proximity_nearest, and mireye_proximity_screen also cover Canada.
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"": {
""mireye"": {
""url"": ""https://mcp.scalekit.com/mireye"",
""headers"": { ""Authorization"": ""Bearer $SCALEKIT_TOKEN"" }
}
}
}
Codex Code REPL
# ~/.codex/config.toml
[mcp_servers.mireye]
url = ""https://mcp.scalekit.com/mireye""
auth_env = ""SCALEKIT_TOKEN""
Copilot Code REPL
# .vscode/mcp.json
{
""servers"": {
""mireye"": {
""url"": ""https://mcp.scalekit.com/mireye"",
""type"": ""http""
}
}
}