Coresignal

by Coresignal-com

1 stars

196 downloads

Not rated

GitHub

About

Access comprehensive B2B data on companies, employees, and job postings for your LLMs and AI workflows.

Details

Author: Coresignal-com
GitHub stars: 1
Downloads: 196
Categories: Developer Tools, Database, Other

Setting up with Highlight

This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:

Download and install Highlight from highlightai.com/download
Navigate to the plugins tab and select "Add Custom Plugin"
Configure the plugin with the settings below

Plugin Name Coresignal

Command (node, npx, python, etc.)

Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
Enable "Start Automatically" if you want the plugin to start when Highlight launches

Setting up with Cursor

Open Cursor's settings
Navigate to the MCP section
Click "Add new Global MCP server"
Copy and paste the configuration below based on your operating system

JSON

{
    "mcpServers": {
        "coresignal": {
            "coresignal_data_api": {
                "command": "npx",
                "args": [
                    "mcp-remote@0.0.22",
                    "https://mcp.coresignal.com/sse",
                    "--header",
                    "apikey:${APIKEY_VALUE}"
                ],
                "env": {
                    "APIKEY_VALUE": "<api_key>"
                }
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "coresignal": {
            "coresignal_data_api": {
                "command": "npx",
                "args": [
                    "mcp-remote@0.0.22",
                    "https://mcp.coresignal.com/sse",
                    "--header",
                    "apikey:${APIKEY_VALUE}"
                ],
                "env": {
                    "APIKEY_VALUE": "<api_key>"
                }
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "coresignal": {
            "coresignal_data_api": {
                "command": "npx",
                "args": [
                    "mcp-remote@0.0.22",
                    "https://mcp.coresignal.com/sse",
                    "--header",
                    "apikey:${APIKEY_VALUE}"
                ],
                "env": {
                    "APIKEY_VALUE": "<api_key>"
                }
            }
        }
    }
}

Setting up with Claude Desktop

Open Claude Desktop's settings
Go to the Integrations tab
Click "Add MCP Server"
Use the configuration below based on your operating system

Note: Make sure Claude Desktop is running before attempting to connect.

JSON

{
    "mcpServers": {
        "coresignal": {
            "coresignal_data_api": {
                "command": "npx",
                "args": [
                    "mcp-remote@0.0.22",
                    "https://mcp.coresignal.com/sse",
                    "--header",
                    "apikey:${APIKEY_VALUE}"
                ],
                "env": {
                    "APIKEY_VALUE": "<api_key>"
                }
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "coresignal": {
            "coresignal_data_api": {
                "command": "npx",
                "args": [
                    "mcp-remote@0.0.22",
                    "https://mcp.coresignal.com/sse",
                    "--header",
                    "apikey:${APIKEY_VALUE}"
                ],
                "env": {
                    "APIKEY_VALUE": "<api_key>"
                }
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "coresignal": {
            "coresignal_data_api": {
                "command": "npx",
                "args": [
                    "mcp-remote@0.0.22",
                    "https://mcp.coresignal.com/sse",
                    "--header",
                    "apikey:${APIKEY_VALUE}"
                ],
                "env": {
                    "APIKEY_VALUE": "<api_key>"
                }
            }
        }
    }
}

Setting up with Windsurf

Open Windsurf's preferences
Go to the Integrations section
Click "Add MCP Integration"
Use the configuration below based on your operating system

JSON

{
    "mcpServers": {
        "coresignal": {
            "coresignal_data_api": {
                "command": "npx",
                "args": [
                    "mcp-remote@0.0.22",
                    "https://mcp.coresignal.com/sse",
                    "--header",
                    "apikey:${APIKEY_VALUE}"
                ],
                "env": {
                    "APIKEY_VALUE": "<api_key>"
                }
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "coresignal": {
            "coresignal_data_api": {
                "command": "npx",
                "args": [
                    "mcp-remote@0.0.22",
                    "https://mcp.coresignal.com/sse",
                    "--header",
                    "apikey:${APIKEY_VALUE}"
                ],
                "env": {
                    "APIKEY_VALUE": "<api_key>"
                }
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "coresignal": {
            "coresignal_data_api": {
                "command": "npx",
                "args": [
                    "mcp-remote@0.0.22",
                    "https://mcp.coresignal.com/sse",
                    "--header",
                    "apikey:${APIKEY_VALUE}"
                ],
                "env": {
                    "APIKEY_VALUE": "<api_key>"
                }
            }
        }
    }
}

Setting up with Cline

Open Cline's settings
Navigate to the Integrations section
Click "Add MCP Server"
Copy and paste the configuration below based on your operating system

Note: Make sure to restart Cline after adding the configuration.

JSON

{
    "mcpServers": {
        "coresignal": {
            "coresignal_data_api": {
                "command": "npx",
                "args": [
                    "mcp-remote@0.0.22",
                    "https://mcp.coresignal.com/sse",
                    "--header",
                    "apikey:${APIKEY_VALUE}"
                ],
                "env": {
                    "APIKEY_VALUE": "<api_key>"
                }
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "coresignal": {
            "coresignal_data_api": {
                "command": "npx",
                "args": [
                    "mcp-remote@0.0.22",
                    "https://mcp.coresignal.com/sse",
                    "--header",
                    "apikey:${APIKEY_VALUE}"
                ],
                "env": {
                    "APIKEY_VALUE": "<api_key>"
                }
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "coresignal": {
            "coresignal_data_api": {
                "command": "npx",
                "args": [
                    "mcp-remote@0.0.22",
                    "https://mcp.coresignal.com/sse",
                    "--header",
                    "apikey:${APIKEY_VALUE}"
                ],
                "env": {
                    "APIKEY_VALUE": "<api_key>"
                }
            }
        }
    }
}

Setting up with Goose

Open Goose's preferences
Go to the Integrations tab
Select "MCP Servers"
Click "Add New Server"
Use the configuration below based on your operating system

JSON

{
    "mcpServers": {
        "coresignal": {
            "coresignal_data_api": {
                "command": "npx",
                "args": [
                    "mcp-remote@0.0.22",
                    "https://mcp.coresignal.com/sse",
                    "--header",
                    "apikey:${APIKEY_VALUE}"
                ],
                "env": {
                    "APIKEY_VALUE": "<api_key>"
                }
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "coresignal": {
            "coresignal_data_api": {
                "command": "npx",
                "args": [
                    "mcp-remote@0.0.22",
                    "https://mcp.coresignal.com/sse",
                    "--header",
                    "apikey:${APIKEY_VALUE}"
                ],
                "env": {
                    "APIKEY_VALUE": "<api_key>"
                }
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "coresignal": {
            "coresignal_data_api": {
                "command": "npx",
                "args": [
                    "mcp-remote@0.0.22",
                    "https://mcp.coresignal.com/sse",
                    "--header",
                    "apikey:${APIKEY_VALUE}"
                ],
                "env": {
                    "APIKEY_VALUE": "<api_key>"
                }
            }
        }
    }
}

From the repository

Connect via a remote SSE endpoint at https://mcp.coresignal.com/sse using the mcp-remote package. You need Node.js installed and an API key. Configure your MCP client with the provided JSON object, setting the APIKEY_VALUE environment variable to your API key.

Claude Desktop / Cursor

Paste into your MCP client config file to install this server.

{
    "mcpServers": {
        "coresignal": {
            "coresignal_data_api": {
                "command": "npx",
                "args": [
                    "mcp-remote@0.0.22",
                    "https://mcp.coresignal.com/sse",
                    "--header",
                    "apikey:${APIKEY_VALUE}"
                ],
                "env": {
                    "APIKEY_VALUE": "<api_key>"
                }
            }
        }
    }
}

McpServers

{
    "coresignal_data_api": {
        "command": "npx",
        "args": [
            "mcp-remote@0.0.22",
            "https://mcp.coresignal.com/sse",
            "--header",
            "apikey:${APIKEY_VALUE}"
        ],
        "env": {
            "APIKEY_VALUE": "<api_key>"
        }
    }
}

- Natural-language company and people search— Ask for B2B SaaS companies in the Nordics or senior Python developers at fintech firms usingentity_searchwith plain-language queries.
- Discover field names by keyword— Useentity_fieldsto find the right field names (e.g., "salary" or "job title") without loading the full 300+ field vocabulary.
- Fetch full or projected records— Pull complete employee, company, or job profiles viaentity_fetchusing search handles (cache_id) or specific IDs, with per-record credit costs.
- Enrich contacts with verified emails— Useemail_enrichto get verified business emails for up to 1,000 employee IDs, with 10 credits charged only for emails found.
- Export large result sets as files— Requestdelivery="url"to get downloadable JSONL files for big fetches, then page through them in-chat with the freeartifact_readtool.

The officialModel Context Protocolserver for Coresignal— bring fresh B2B data on895M+ employees,70M+ companies, and468M+ job postingsstraight into your AI assistant.

Search in plain natural language, pull full records, enrich contacts with verified emails, and export large result sets as downloadable files — all from Claude, Cursor, Codex, VS Code, or any other MCP-compatible client.

- A Coresignal accountwith an active subscription (credits) and a team API key provisioned in the dashboard. The MCP server resolves your team's key automatically after sign-in — you never paste it into a config file. No subscription yet? Start with the7-day free trial— it includes2,000 credits. See the plan comparison.

Claude Desktop supports remote MCP servers natively viaConnectors:

Important — enable file downloads:Claude Desktop blocks downloads from domains it doesn't know. To download result files (large fetches are delivered as links), addmcp.coresignal.comto theDomain allowlistin Claude Desktop settings (on Team/Enterprise plans your admin manages this). Without it, download links from the server will be blocked — though you can always read the data back in-chat with the freeartifact_readtool instead. See File downloads.

claude mcp add --transport http coresignal https://mcp.coresignal.com/mcp/v2

Then inside a session run/mcp, selectcoresignal, and complete the browser sign-in. Re-run/mcpany time you need to re-authenticate.

codex mcp add coresignal --url https://mcp.coresignal.com/mcp/v2

{ "mcpServers": { "coresignal": { "url": "https://mcp.coresignal.com/mcp/v2" } } }

Cursor detects that the server requires authentication and shows aNeeds loginprompt — click it to complete the browser sign-in.

opencode mcp add coresignal --url https://mcp.coresignal.com/mcp/v2

RunMCP: Add Serverfrom the Command Palette, chooseHTTP, and enter the URL — or add to.vscode/mcp.json:

{ "servers": { "coresignal": { "type": "http", "url": "https://mcp.coresignal.com/mcp/v2" } } }

VS Code prompts you to authorize the server on first use and handles the OAuth flow in your browser.

Add to~/.cline/data/settings/cline_mcp_settings.json:

{ "mcpServers": { "coresignal": { "type": "streamableHttp", "url": "https://mcp.coresignal.com/mcp/v2", "disabled": false } } }

From menu selectAuthorize OAuthand selectcoresignal. Cline will handle the OAuth flow in your browser.

File downloads & the domain allowlist

Large results (and any call withdelivery="url") are not dumped into the chat to save LLM input tokens. Instead the server stores the rows as a file and returns asigned HTTPS download linkthat expires after1 hour:

{ "delivery": "url", "url": "https://mcp.coresignal.com/mcp/v2/artifacts/…?exp=…&sig=…", "artifact_name": "employee_fetch-baf941dd4f8c4dfe.jsonl", "count": 500, "credits_consumed": 10000 }

From here, the agent gets at the data in one of three ways:
- The agent downloads the file itself— in clients with shell access, the agent will typicallycurlthe link to disk and analyze the file locally withgrep/jq/pandas.
- The agent reads it back in-chat— in clients with no shell and no filesystem, the agent callsartifact_read(artifact_name, offset, limit)instead, paging through the file in slices over the MCP session. This isfreeand works everywhere, so nothing floods the chat.
- You download it manually— if the agent itself isn't allowed to fetch the link (domain not allowlisted, sandbox without network access), click the link, save the file, and tell the agent where it is:"I've downloaded the file to ~/Downloads/employee_fetch-….jsonl — analyze it from there."Works in any client that can read local files.

Prefer the download when your client supports it.artifact_readis free in Coresignal credits, but not in LLM tokens: every page it returns becomes part of the conversation and is re-billed as input tokens on each subsequent turn. Each page is also trimmed to a fixed token budget — a full employee record is ~8k tokens, so a single page carries only a handful of full records regardless of thelimityou ask for. Reading a large file that way takes hundreds of calls and can exhaust the context window before you reach the end. A downloaded file costs essentially no tokens — the assistant can filter thousands of rows locally withgrep/jqand surface only the answer. That's why it pays to get downloads working up front (domain allowlist, sandbox network access) and keepartifact_readfor clients that can't download or for eyeballing a few rows.

If downloads are blocked, nothing is lost:the records are already stored and paid for — read them withartifact_read. Never re-run a fetch to "recover" a file; that bills every record a second time.

Searchesemployee,company, orjobrecords with a plain-language query:

"Senior Python developers at fintech companies in French"

Every call costs a flat20 creditsand returns:

- total_count— the exact number of records the query matched,
- up to 20 preview rows (limit=0returns just the count), each showing the fields the query matched on — theevidencefor why each result is there,
- acache_id— a 1-hour handle to the search thatsaves credits and time: pass it toentity_fetchand the matched records are collected straight away — no need to re-run (and re-pay for) the search, and resolving thecache_iditself is free. Record ids stay server-side, so nothing bulky ever passes through the conversation.

Free, instant lookup of field names by meaning —"salary"finds the compensation fields,"current job title and seniority"findsactive_experience_title,experience.position_title, etc. Use it to build thefieldslist for a custom-scope fetch without ever loading the full field vocabulary into context.

Collects records — either up to 20 hand-picked ids from search results, or up to1,000 records per callvia acache_id. Billing is per record found:20 creditsfor employees/companies,1for jobs.

Verified, deliverable business emails for up to 1,000 employee ids —10 credits per email found; not-found ids are free. EEA/UK contacts are not accessible (GDPR).

Reads a delivered file back over the authenticated MCP session, a page at a time —free, since the records were billed when they were fetched. This is what makes file delivery work everywhere, including chat clients that can't open a link or touch a filesystem.

"Find B2B SaaS companies in the Nordics with 50–200 employees that raised funding in the last two years."

"Search for heads of data at US companies with 500+ employees. Fetch 20 full profiles to a file with verified emails."

"Pull the full record for flo.health — funding rounds, headcount growth, and current job openings."

Every response includescredits_consumed— the actual billed amount, so a discrepancy (sent 1,000 ids, billed for 950 records) tells you exactly how many ids weren't found. The server never spends silently: fetches confirm field scope with you first, and a fetch that can't be delivered failsbeforeany credits are spent.

Credits are drawn from your team's Coresignal subscription — manage keys and billing in the dashboard. New to Coresignal? The7-day free trial comes with 2,000 credits— that's 100 searches, or 100 employee/company records, or a mix — see the plan comparison.

- Coresignal— data coverage, plans, and pricing
- Coresignal dashboard— account, team, API keys, credits
- API documentation— the underlying data APIs

Real-time comprehensive company data enrichment for AI agents. Look up industry, employee count, founding year, headquarters, social profiles, and brand assets for any company - by domain or stock ticker. Works in every MCP-compatible client.

A read-only MCP server by CData for querying live Zoho Creator data using a JDBC driver.

DataForB2B is a people and company search API

Access comprehensive company data including financial records, ownership structures, and contact information. Search for businesses using domains, registration numbers, or LinkedIn profiles to streamline due diligence and lead generation. Retrieve historical financial performance and complex corporate group structures to support informed business analysis.

PredictLeads MCP lets AI agents securely access PredictLeads datasets - including jobs, news, funding, technologies, connections, and company data

Find buying signals for companies and contacts

Skyvia MCP Endpoint is a no-code gateway that makes your business data accessible to AI assistants in real time.

Read-only MCP server for the SAP analytics services market — consulting firms, contract radar, day rates, concepts, studies and news across SAP Datasphere, Business Data Cloud, SAC, BW/4HANA and Databricks.

Prospection B2B en France — sourcing entreprises, enrichissement contacts, push CRM. Remote MCP server avec OAuth 2.1.

Validates business ideas with one focused MCP call instead of a long manual research loop. Returns structured scores, risk flags, and competitor context.

No reviews yet — be the first

Use Google, GitHub, or an email account so ratings stay tied to real people.

Email sign in

No reviews posted yet.

Coresignal

About

Details

Jump to

Setting up with Highlight

Setting up with Cursor

JSON

JSON

JSON

Setting up with Claude Desktop

JSON

JSON

JSON

Setting up with Windsurf

JSON

JSON

JSON

Setting up with Cline

JSON

JSON

JSON

Setting up with Goose

JSON

JSON

JSON

From the repository

Claude Desktop / Cursor

McpServers

File downloads & the domain allowlist

Install

About

Details

Jump to

Setting up with Highlight

From the repository

Claude Desktop / Cursor

McpServers

File downloads & the domain allowlist

Install

More like this

Sequential Thinking

Redis

Sentry

Github

Filesystem

EverArt