Analytics
StreetLight Data MCP connector
The StreetLight Data connector lets Claude, ChatGPT, Cursor and the Elaichi Agent create zone sets, launch and track analyses, read metrics and segment counts, and manage tags inside StreetLight Data, all under each person's own access.
-
How it connects. Connects with an API key. The credential goes into a vault nobody reads back.
-
One address. https://api.elaichi.ai/mcp, the same for every user.
-
Their own access. An agent never gets more than the person it acts for.
How to connect
How to connect StreetLight Data to Claude, ChatGPT or Cursor
Two steps, about a minute.
In Elaichi
Connect StreetLight Data once
-
Open Connections, choose Add connection, and pick StreetLight Data.
-
Optionally set Share with to give a team access, then press Connect.
-
Paste a StreetLight Data API key. One person generates a token in StreetLight Data and pastes it once. Everyone else works through Share with, and never sees it.
The credential is vaulted. Nobody reads it back, not even the AI.
Add connection
Choose a connector.
In your AI client
Point it at one endpoint
Everyone in the organization uses the same address, and each person only ever reaches what their own account allows.
Connect StreetLight Data to Claude
-
1
Open Customize, then Connectors.
-
2
Press Add.
-
3
Name it, paste the MCP server URL, then Continue.
https://api.elaichi.ai/mcp -
4
Sign in and approve.
On Team and Enterprise, an Owner adds it once. Everyone else turns it on for themselves.
Connect StreetLight Data to ChatGPT
-
1
Open Plugins, then press the + button.
-
2
Name it and paste the endpoint into Server URL.
https://api.elaichi.ai/mcp -
3
Leave Authentication on OAuth, then tick the risk acknowledgement.
-
4
Press Create, then sign in and approve.
Works on the web today. The plugin directory lives at chatgpt.com/plugins.
Connect StreetLight Data to Cursor
-
1
Open
~/.cursor/mcp.json. -
2
Add the endpoint under
mcpServers.https://api.elaichi.ai/mcp -
3
Reload Cursor, then sign in and approve.
~/.cursor/mcp.json
{
"mcpServers": {
"elaichi": {
"url": "https://api.elaichi.ai/mcp"
}
}
}
Set up per machine, so repeat it on each computer you work from.
Connect StreetLight Data to any MCP client
-
1
Add the endpoint as a remote MCP server.
https://api.elaichi.ai/mcp -
2
Sign in and approve.
{
"mcpServers": {
"elaichi": {
"url": "https://api.elaichi.ai/mcp"
}
}
}
The Elaichi Agent already has these tools, with nothing to set up.
Use cases
What teams do with StreetLight Data through Elaichi
Every one of these runs inside the access the person already has, and lands in the same audit log.
-
Planning
Set up a corridor study in plain language
Describe the corridor and the date range you care about, and the agent builds the zone set and launches the analysis in StreetLight Data for you.
-
Traffic engineering
Pull segment counts for a signal review
Ask for volumes on the segments around an intersection and get the segment counts and metrics read back, ready to drop into the review memo.
-
Consulting
Check which client analyses are still running
List the analyses for a project, see which are finished, and cancel one that was launched with the wrong settings before it uses more of the account.
-
GIS
Find the right OSM IDs for a street
Search StreetLight Data for the OSM IDs along a named road so a new zone set lands on the correct segments the first time.
-
Public works
Tag analyses by grant or project
Create a set of tags in one go and attach them to the analyses for a grant program, so every study can be found by project later.
-
Research
Read finished metrics without opening the console
Ask for the metrics of a completed analysis by name and get a plain summary of what the numbers say, including which date ranges were covered.
Try asking
- “List every analysis still running for the Route 9 corridor study”
- “Show segment counts from the Main Street analysis for last spring”
- “Tag all analyses for the I-80 grant with the project name”
AI tools
StreetLight Data tools for your AI agents
24 tools are ready to call through Elaichi's MCP endpoint the moment you connect StreetLight Data, governed by the same roles, restrictions, and audit log as everything else in Elaichi.
No tools match your search.
See it in Elaichi
What connecting StreetLight Data gets you
6 screens from the product, each doing one job for your StreetLight Data account.
The agent
Ask about traffic studies in plain language.
Zone sets, analyses and segment counts answered from live StreetLight Data records.
- zone sets
- analyses
- tags
- segment counts
Ask Elaichi to work across your apps.
List every analysis still running for the Route 9 corridor study
Show segment counts from the Main Street analysis for last spring
Tag all analyses for the I-80 grant with the project name
Also runs in Claude, ChatGPT or Cursor
MCP clients
One endpoint reaches StreetLight Data from every client.
Claude, ChatGPT and Cursor share one governed endpoint, no SDK and no shared API key.
Copy the endpoint
Tool catalog
24 StreetLight Data tools, no code to write.
Zone sets, analyses, tags, metrics and segment counts, covered out of the box.
- Create a StreetLight Data debug
- Create a StreetLight Data zone set
- List all StreetLight Data zone sets
- StreetLight Data osm IDS search
Toolboxes
Every team gets its own StreetLight Data toolbox.
Planners, engineers and consultants each work from a toolbox scoped to their team.
- Planning
- Traffic engineering
- Consulting
- GIS
Shared connections
Teammates run analyses without seeing the key.
One person connects StreetLight Data, shares it, and nobody else handles the API key.
- Long range planning
- Traffic engineering
- GIS
- Consulting
Audit log
Know who launched every StreetLight Data analysis.
When, who, what happened and which analysis, kept in an append-only log.
- When
- Who
- What happened
- Type
Launching soon
From answering questions to doing the work
A person no longer has to ask. A trigger starts the work, inside the same permissions and the same audit log as everything else. Automations and live dashboards are launching soon, on the Black plan.
Automations
A schedule turns finished analyses into a digest.
Analyses are fetched, grouped, drafted, approved by a person, then tagged back in StreetLight Data.
StreetLight Data digest
Run 418 · started 2 minutes ago · on behalf of Emma Laurent
-
✓
Schedule
Every weekday at 08:00
0.2s -
✓
Fetch zone sets
StreetLight Data
1.4s -
✓
Group by owner
Transform
0.1s -
✓
Draft the digest
Agent step
Ran with 4 tools, returned a structured summary
6.2s -
Approve the digest
Needs approval
Assigned to Michael Brennan
Approve Deny -
Post the digest
StreetLight Data
Queued
Collections and dashboards
StreetLight Data health, computed with no model.
Four metrics, 14 days of analyses created and a team breakdown, refreshed on schedule.
StreetLight Data health
Refreshed 4 minutes ago · every 15 minutes · from the zone sets collection
Zone sets
1,284 ↓ 12%
Analyses
96 ↓ 8%
Needs attention
3 ↑ 2
Updated this week
412 ↑ 9%
Zone sets created
Last 14 days
By team
Share of activity
Long range planning 34%
Traffic engineering 27%
GIS 21%
Consulting 18%
Related connectors
More from the catalog
FAQ
Frequently asked questions
How do I connect StreetLight Data to Claude?
Connect StreetLight Data in Elaichi by pasting in your StreetLight Data API key. Then in Claude, open Customize, then Connectors, then Add, and paste the endpoint https://api.elaichi.ai/mcp. There is no OAuth application to register and no client ID or secret to generate, and the whole thing takes a few minutes.
Does StreetLight Data work with ChatGPT and Cursor as well as Claude?
Yes. Once StreetLight Data is connected in Elaichi, the same endpoint, https://api.elaichi.ai/mcp, works in Claude, ChatGPT, Cursor, any other MCP client and the Elaichi Agent. You connect StreetLight Data once and every client picks it up.
What can an AI agent actually do with my StreetLight Data account?
An agent connected to StreetLight Data can create zone sets, search OSM IDs, launch, update or cancel analyses, and list what is running or finished. It can read the metrics, geometries and segment counts from completed analyses, check available date ranges and account usage, and create or remove tags to keep projects organized.
Does connecting StreetLight Data give the AI access to everything in the account?
No. Every call into StreetLight Data runs under the access of the person who signed in to Elaichi, so the AI can only see the analyses, zone sets and metrics that person could already see. Elaichi can narrow that access further with restrictions, and it can never widen it beyond what StreetLight Data itself allows.
Can I stop an agent from deleting or changing things in StreetLight Data?
Yes. Restrictions in Elaichi apply per action, so you can allow reading StreetLight Data metrics and segment counts while blocking the actions that delete analyses, cancel them or remove tags. A blocked action is never advertised to the AI client at all, so no prompt can reach it.
What happens to a StreetLight Data connection when someone leaves?
Offboarding a person in Elaichi ends their access to StreetLight Data through every client at once. A shared StreetLight Data connection keeps working for everyone else on the team. If you ever want to remove StreetLight Data entirely, disconnecting it once in Elaichi removes it from Claude, ChatGPT, Cursor and every other client.
Put StreetLight Data in front of your team
Fourteen days on Gold, no credit card. Connect it once and pick what each team can call.