Install
$ agentstack add mcp-spekoai-mcp-bridge ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v1.0.10 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v1.0.10. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
@spekoai/mcp
Interactive installer and local stdio-to-remote bridge for Speko MCP. The installer configures Speko's hosted remote MCP endpoint in coding tools that support it. The bridge command is only for MCP clients that require a local stdio command: it speaks stdio to the client, connects to Speko's hosted MCP server over HTTP, and does not contain Speko tool logic of its own.
Install
npx @spekoai/mcp@latest init
The package exposes the spekoai-mcp binary. Run init for a guided setup wizard that can configure Claude Code, Codex, OpenCode, Cursor, and generic MCP clients.
For scripted setup, pass the choices explicitly:
npx @spekoai/mcp@latest init --auth oauth --tools claude,codex --scope user --yes
Bridge
Most users should run init. Use bridge only when a client cannot connect to remote MCP directly and asks for a local command-based MCP server.
npx @spekoai/mcp@latest bridge
For API-key auth in a headless bridge setup, provide SPEKO_API_KEY in the MCP client environment. The bridge forwards it to the hosted MCP server as Authorization: Bearer ....
The bridge command adapts local stdio MCP to Speko's remote HTTP MCP endpoint. Use direct remote MCP configuration instead when your client supports it.
Defaults:
- Endpoint:
https://mcp.speko.ai/mcp
Environment variables:
SPEKO_API_KEY: forward an API key as a bearer token.
CLI examples:
npx @spekoai/mcp@latest bridge
SPEKO_API_KEY=sk_live_xxx npx @spekoai/mcp@latest bridge
All remaining arguments are passed through to mcp-remote.
Troubleshooting
Run:
npx @spekoai/mcp@latest bridge --help
When using bridge, OAuth state is handled by mcp-remote. It may create a local OAuth cache directory, or use MCP_REMOTE_CONFIG_DIR to store local OAuth credentials and debug logs. The init wizard does not write that directory.
For connection or OAuth issues, pass --debug and inspect the log path printed by mcp-remote.
Source & license
This open-source MCP server is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: SpekoAI
- Source: SpekoAI/mcp-bridge
- License: MIT
- Homepage: https://docs.speko.dev/quickstart/mcp
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v1.0.10 Imported from the upstream source.