MCP SERVER
opencode-bridge
linking Claude Code to OpenCode
multi-model consultation, framed by domain
pip install opencode-bridge
Claude Code
primary
query
review
plan
synthesize
OpenCode Hub
companion
GPT-5
Gemini
Other
Claude Code
MCP
OpenCode Hub
Model
Hub
Claude Code
01
Install
$ pip install opencode-bridgerequires: Python 3.10+ · Claude Code · OpenCode CLI
then add to your MCP config:
{ "opencode-bridge": { "command": "opencode-bridge" } }02
Capabilities
multi-model
consult GPT-5, Gemini, others via OpenCode
auto-framing
detects domain and frames as specialized expert
code review
file-level analysis with adaptive strategies
chunked map-reduce
2K+ line files split, processed in parallel, synthesized
sessions
start, switch, end, export conversation history
planning
dedicated plan agent for task decomposition
brainstorming
open-ended ideation through alternate perspectives
03
How It Works
1
Claude Code sends query via MCP
2
opencode-bridge auto-detects domain
3
routes to OpenCode with expert framing
4
OpenCode consults model
5
response synthesized and returned to Claude
04
MCP Tools 18
Core
opencode_discuss
send a message, auto-framed by domain
opencode_plan
planning discussion with plan agent
opencode_brainstorm
open-ended brainstorming
opencode_review
code review with chunked large-file support
Session
opencode_start
start a new session
opencode_end
end current session
opencode_switch
switch between sessions
opencode_sessions
list all sessions
opencode_history
get conversation history
opencode_export
export transcript as markdown/JSON
Configuration
opencode_models
list available models
opencode_agents
list available agents
opencode_model
change session model
opencode_agent
change session agent
opencode_variant
change reasoning effort
opencode_config
get current config
opencode_configure
set defaults (persisted)
opencode_health
server health check
05
Auto-Framing
When Claude sends a message, opencode-bridge detects the domain and frames OpenCode as a specialized expert.
architecture
debugging
performance
security
testing
devops
database
api_design
frontend
algorithms
code_quality
planning
general
06
Chunked Processing
For files over 2,000 lines:
split
overlapping chunks · 800 lines · 20-line overlap
snap
language-agnostic boundary detection · functions, classes
parallel
up to 6 chunks processed concurrently
synthesize
results merged into single coherent response
input
4,200 lines
chunks
output
synthesized