Provider REST API

13 actions

Connect Claude to Semgrep

Read code, supply-chain and secrets findings from the Semgrep AppSec Platform, triage them, and manage projects. Toolspoke puts 13 of its actions behind one MCP endpoint that Claude, Cursor, and Codex all speak.

Connect View pricing

Connection: Provider REST API
Authentication: API token
Actions exposed: 13
What a call bills: Nothing
Adapter: Maintained by Toolspoke

Connected in three steps

1
Install Semgrep
Open the marketplace in your workspace, add Semgrep to the project your agents work in, and it appears on the gateway immediately.
2
Connect the credential
Authenticate with api token. Where to get one, and what it has to be able to reach, is the next section.
3
Point your agent at the gateway
Give your client one address, https://toolspoke.com/mcp. Claude Code takes it as a command, Claude and Claude Desktop add it as a custom connector, and Cursor, Codex and VS Code each read it from a config file of their own.

.mcp.json

{
  "mcpServers": {
    "toolspoke": {
      "type": "http",
      "url": "https://toolspoke.com/mcp"
    }
  }
}

One block covers every tool you have installed. Semgrep shows up in the client as soon as your policy allows it, and so does everything else you install later.

Where the address goes, per client

Claude Code: Run it in your project, then /mcp to sign in
claude mcp add --transport http toolspoke https://toolspoke.com/mcp
Claude and Claude Desktop: Settings, then Connectors, then Add custom connector
https://toolspoke.com/mcp
Cursor: ~/.cursor/mcp.json, or .cursor/mcp.json for one project
{ "mcpServers": { "toolspoke": { "url": "https://toolspoke.com/mcp" } } }
Codex: ~/.codex/config.toml
[mcp_servers.toolspoke] url = "https://toolspoke.com/mcp"
VS Code: .vscode/mcp.json, or the MCP: Add Server command
{ "servers": { "toolspoke": { "type": "http", "url": "https://toolspoke.com/mcp" } } }

What Semgrep asks for

API token. You provide it once, when you install the connector. Toolspoke encrypts it at rest and decrypts it only for the length of a single call, and the gateway attaches it to the outbound request itself, so it is never part of the arguments an agent sends.

API tokenRequired: Semgrep AppSec Platform → Settings → Tokens → API tokens → Create new token, and tick Web API. A token without Web API access is refused by every call here.; 64 hex characters

What Claude can do in Semgrep

13 actions, each one declared and named by the connector rather than discovered at runtime. A workspace policy grants a person all of them, a hand-picked selection, everything on the read side, everything on the write side, or none.

Reads: 9Reads
Writes: 3Writes
Destructive: 1Destructive

Reads

Fetches data and changes nothing.

list_deployments
Return the deployment (organization) this token can reach, with its slug and numeric id. Every other call needs one of the two, and a token without Web API access fails here, which is why an install tests itself with it.
list_projects
List the projects (repositories) that have been scanned or onboarded to Managed Scans, 100 per page by default. Archived repositories are left out.
get_project
Read one project's details - its URL, tags, latest scan and Managed Scans state.
list_findings
List code (sast), supply-chain (sca) or AI-detected (ai_sast) findings, 100 per page, filtered by repository, status, severity, branch, rule or triage reason. Each finding carries its rule, location, severity, status and triage history; its id is what triage_findings takes.
list_secrets
List Semgrep Secrets findings - leaked credentials found in code - with their validation state. The response names where each secret was found and whether Semgrep could confirm it is live, not the secret's value; it is still kept out of the audit log.
search_scans
List scans from the past 30 days, optionally for one repository or branch. Use it to answer "did the last scan run" and to get a scan id for get_scan.
get_scan
Read one scan with its repository, commit, branch, status and timing.
list_policies
List the deployment's policies - the rule sets and modes (monitor, comment, block) that decide what a scan reports.
list_dependencies
List the open-source dependencies Semgrep Supply Chain found across the deployment's repositories, paged by cursor.

Writes

Creates or updates something on the other side.

triage_findings
Set the triage state of findings by id: ignored, reviewing, fixing, reopened or provisionally_ignored, with a reason and a note. A write rather than destructive because every state can be reopened. Ignoring a finding hides it from every PR comment and block, so do it only when asked.
add_project_tags
Add tags to a project. Tags that do not exist yet are created. Tags are what policies and finding filters group projects by.
remove_project_tags
Remove tags from one project. The tags themselves stay on the deployment and can be added back with add_project_tags.

Destructive

Deletes or permanently alters something. Worth granting on purpose.

delete_project
Delete a project and every finding recorded against it. There is no undo - the findings history and its triage notes are gone, and a later scan starts the project from nothing.

What it will not do

Enforced by the gateway rather than left to convention, which is why each of these can be stated flatly.

It cannot call anything else: The 13 actions above are the whole of it. A call to any other name is refused before it reaches Semgrep rather than forwarded on, and connecting your account does not add to the list: it is fixed by the connector, not discovered at run time.
It reaches no further than your credential: Toolspoke holds no access to Semgrep of its own. Every call carries the credential you stored and nothing besides, so whatever that credential cannot reach, this connector cannot reach either.
It never hears from Semgrep: Nothing is pushed to it. There is no webhook, no subscription and no polling, so this connector cannot notice by itself that something changed in Semgrep. An agent has to ask.
It does not smooth over provider limits: Toolspoke does not retry, queue or back off around Semgrep's own rate limits. A call that Semgrep refuses comes back to the agent as a failed call.

Before you connect it

What can Claude do in Semgrep?

13 named actions: 9 that only read, 3 that write and 1 that delete or permanently alter something. They include list_deployments, list_projects and get_project. Nothing outside that list is reachable: the connector declares each operation by name rather than proxying whatever an agent asks for.

What credentials does the Semgrep connector need?

API token. The connector asks for api token. Values are encrypted at rest and attached to the outbound request by the gateway, so they are never part of the arguments an agent sends and never reach the audit log.

Does the Semgrep connector work with Cursor and Codex, or only Claude?

Any client that speaks MCP, and every one of them gets the same 13 actions. There is a single address, https://toolspoke.com/mcp. Claude Code adds it with claude mcp add --transport http, Claude and Claude Desktop take it as a custom connector in settings, Cursor reads it from .cursor/mcp.json, Codex from ~/.codex/config.toml, and VS Code from .vscode/mcp.json. Each of them signs in to the gateway itself, so there is no key to paste.

What does the Semgrep connector not do?

The 13 actions above are the whole of it. A call to any other name is refused before it reaches Semgrep rather than forwarded on, and connecting your account does not add to the list: it is fixed by the connector, not discovered at run time. Toolspoke holds no access to Semgrep of its own. Every call carries the credential you stored and nothing besides, so whatever that credential cannot reach, this connector cannot reach either. Nothing is pushed to it. There is no webhook, no subscription and no polling, so this connector cannot notice by itself that something changed in Semgrep. An agent has to ask. Toolspoke does not retry, queue or back off around Semgrep's own rate limits. A call that Semgrep refuses comes back to the agent as a failed call.

Can I limit which actions an agent can call?

Yes, in two places. The project switches Semgrep's actions on and off one at a time, for everyone in the project at once, and the screen groups them by read, write and destructive so turning off everything that deletes is one click. An individual agent key can then be narrowed further, to particular toolkits in a project and to particular actions in a toolkit. Whatever it was granted, a key never reaches a project its owner cannot.

What gets recorded when an agent calls Semgrep?

Every attempt, with the agent that made it and the person that agent belongs to, the full request payload, the response payload, the status, the duration, and what the call cost in sandbox time and model tokens. Values whose key names a secret are masked out before the record is shown to anyone. An operation the connector marks as not retained never has its response body written at all, so the gateway keeps no second copy of what was read.

More security connectors

Browse all of them