MCP Gateway · Claude Code
Connect Glyphic to Claude Code
Prospects describe integration needs and product gaps on sales calls, and that detail rarely reaches the engineer building the fix. Glyphic gives Claude Code access to sales call transcripts and deal insights, so you can check what a customer actually asked for before writing code. Agent hooks send each tool call to Speakeasy, which allows or denies it first.
- Category
- Sales & CRM
- Authentication
- API key
- Claude Code
- CLI
Behind the MCP Gateway
Run Glyphic MCP behind the MCP Gateway
One URL for every agent, sign-in through your IdP, RBAC down to the tool, and every Glyphic call inspected and logged.
Set up
Add Glyphic to Claude Code in 4 steps
- 01
Add Glyphic from the catalog
An admin finds Glyphic in the MCP Catalog (MCP Gateway > MCP > Catalog) and clicks Add. Speakeasy registers the vendor's server as a remote MCP server and proxies sessions to it. Nothing is copied or re-hosted.
Glyphic authenticates with an API key. Enter it under Upstream headers in the install dialog, or later on the server's Settings tab. The key is stored on the server, sent with every upstream request, and never reaches anyone's client configuration.
Where MCP-scoped policies are enabled, the install offers a recommended risk policy for the new server that detects secrets and PII and inspects tool requests and responses.
- 02
Choose who can use Glyphic
Give teams the
mcp:connectscope on the Glyphic server through team access or a role. The organization gateway works out each person's servers from their live access, so granting access adds Glyphic to their gateway on the next call, and removing it takes it away. - 03
Connect Claude Code
Add the organization gateway as an HTTP MCP server, then authenticate from /mcp.
Run the command below with your organization gateway URL.
Open
/mcpin Claude Code and choose Authenticate to sign in.claude mcp add --transport http --scope user \ 'speakeasy' \ 'https://<organization host>/mcp/gateway/<organization slug>' - 04
Sign in and use Glyphic from Claude Code
The first time Claude Code connects, it opens a browser so the person can sign in to Speakeasy through your identity provider.
From then on, Glyphic's tools appear in Claude Code, limited to what the person's access allows, and every call lands in the gateway's tool logs.
To roll it out to a whole team, publish the server in a plugin and register the plugin marketplace in Claude Code's managed settings, so every member gets it without running the command. The device agent can also write and reapply these settings on each laptop.
Use cases
What Claude Code users do with Glyphic
Check what a prospect asked for
Before building a feature promised in a deal, ask Claude Code to find the sales call where it came up and quote the prospect's exact requirements from the transcript.
Size demand for a feature request
Claude Code searches Glyphic's deal insights for how often a missing integration is mentioned in sales calls, and adds the count to the design proposal.
Reproduce a bug raised in a demo
When something broke during a sales demo, Claude Code reads the call transcript to find what the presenter clicked and the error they hit, then writes a failing test.
Control
What Speakeasy can see and stop in Claude Code
The gateway covers every client the same way. The rest depends on what Claude Code exposes to Speakeasy.
Tool logs
Gateway
Every Glyphic call is logged with the person and the client that made it.
Access by role
Gateway
People reach only the Glyphic tools their team or role allows.
Request and response blocking
Gateway
A risk policy scoped to Glyphic can reject a tool request before it reaches the server, or withhold a result from Claude Code. MCP-scoped policies are enabled per organization.
Prompt and tool-call blocking
Claude Code
Agent hooks send each prompt and tool call to Speakeasy, which allows or denies it before Claude Code runs it.
User attribution
Claude Code
Claude Code's OpenTelemetry exporter ties each session to a named person. Without it, activity can't be attributed.
Budgets
Claude Code
Spend limits can block Claude Code traffic once a budget is reached.
Device agent and MDM
Claude Code
The device agent installs the marketplace, plugin and telemetry settings and reapplies them every minute. It deploys through MDM.
Anthropic inference hooks
Claude Code
On Claude Enterprise, prompts can be checked before inference with nothing installed on the device (beta).
- Claude Code on the web doesn't use the laptop setup. It needs the device agent in a shared Anthropic-hosted environment.
- Plugin marketplace URLs for Claude Code carry an access token, so share install snippets only through a private channel.
Questions
Frequently asked questions
Do developers need a Glyphic API key in Claude Code?
Can Claude Code activity with Glyphic be attributed to a person?
How do Claude Code users get Glyphic?
Are Glyphic calls from Claude Code logged?
Connect more