opencode-mcp-bridge (teodorgross/opencode-mcp-bridge) is an MCP server listed on the M8ven Trust Index. M8ven has not graded it: we have no way to read this server ourselves. No publisher has claimed this listing.
A local MCP server that delegates coding tasks to a temporary OpenCode session and returns a completion report with changed files, tool calls, cost, and the subagent's reply.
Emerging. No concerning findings. Grades remain capped until the project builds reputation through adoption. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.
How we verified
Verified is a snapshot. Live keeps it current, and builds your track record.
⚡ Connect GitHub → continuous verification on every pushwhy connect →Who stands behind it
teodorgross
Source: Glama
Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find. Or connect your repo for our deepest verification, Live Monitored: read-only, revoke anytime. What we access →
Install from
M8ven verifies MCPs across every public registry — install directly from whichever one you prefer.
ComSpecOPENCODE_MCP_AGENTOpenCode agentOPENCODE_MCP_ALLOWED_DIRECTORIESdirectories a run may work in, separated by the platform's path delimiterOPENCODE_MCP_ALLOW_REMOTEstartup unless you set =1 yourself. The setting is not reachableOPENCODE_MCP_DIRECTORYdefault working directoryOPENCODE_MCP_EFFORTResolution order matches the model's: dispatch parameter → stored config →OPENCODE_MCP_HOMEConfig file — ~/.opencode-mcp-bridge/config.json (or wherever points):OPENCODE_MCP_LOCKmodel,permissionModeOPENCODE_MCP_LOG_FILEalso append log lines to this fileOPENCODE_MCP_LOG_LEVELsilent / error / warn / info / debugOPENCODE_MCP_MAX_CONCURRENT_RUNSruns in flight at onceOPENCODE_MCP_MAX_COST_USDhard ceiling per run in dollarsOPENCODE_MCP_MODELdefault model as provider/modelOPENCODE_MCP_PERMISSION_MODEauto / readonly / strictOPENCODE_MCP_PORTport for the spawned serverOPENCODE_MCP_RETRY_ATTEMPTStotal attempts per HTTP call; 1 disables retryingOPENCODE_MCP_RETRY_BASE_MSfirst backoff step in millisecondsOPENCODE_MCP_SERVER_URLuse an existing OpenCode server instead of spawning one. Loopback only by defaultOPENCODE_MCP_SKIP_VERSION_CHECK1 lifts the refusal if you want to try anyway.SELFTEST_DIRSELFTEST_MODELAll four hints declared on every tool
16/19 tools missing one or more hints — opencode_health (missing: destructiveHint, idempotentHint); opencode_agents (missing: destructiveHint, idempotentHint); opencode_models (missing: destructiveHint, idempotentHint), +13 more. OpenAI's directory rejects tools where any of the four hints are missing or non-boolean.
For every tool, set all four hints (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) to explicit true/false values that match the handler’s actual behaviour.
Tool inputs are validated
18/19 tool handlers declare input schemas (95%)
Declare an inputSchema with zod/joi/yup on every tool definition.
Tests exist
No test files found
Add tests that exercise each declared tool.
Shell command execution
18 child_process calls — runs shell commands
Prefer library functions over shell-outs. If you must shell out, ensure all inputs are properly escaped.
Claim the listing to review these findings one by one and send us a correction where you disagree, straight to the team. Claiming also means we tell you when the grade moves, and reach you first if we find anything urgent.
[](https://m8ven.ai/mcp/teodorgross-opencode-mcp-bridge-kvbo20)?variant=verified to the badge URL.Vetting this one by hand? Tool Check is an MCP that scores other MCPs. Add it once and ask Claude, ChatGPT, or any MCP client to grade a server, surface CVEs, check the publisher, and suggest safer alternatives — before you install.
https://m8ven.ai/api/mcp/tool-check