LLM-bridge-mcp-server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| ZAI_API_KEY | Yes | API key for the Z.AI or OpenRouter provider | |
| ZAI_PROVIDER | No | Provider selection: 'zai' or 'openrouter' | zai |
| ZAI_TEXT_MODEL | No | Model identifier for text generation tasks | |
| ZAI_API_BASE_URL | No | Base URL for the API provider | |
| ZAI_VISION_MODEL | No | Model identifier for vision/UI audit tasks | |
| GLM_BRIDGE_DATA_DIR | No | Directory path for persistent data storage | |
| GLM_BRIDGE_HTTP_HOST | No | Host address for HTTP transport mode | |
| GLM_BRIDGE_HTTP_PORT | No | Port for HTTP transport mode | |
| GLM_BRIDGE_LOG_LEVEL | No | Logging level (e.g., 'debug', 'info', 'error') | |
| GLM_BRIDGE_TRANSPORT_MODE | No | Transport mode: 'stdio' for local MCP, 'http' for remote streamable HTTP | stdio |
| GLM_BRIDGE_ALLOWED_DOMAINS | No | Comma-separated allowed domains for network retrieval | |
| GLM_BRIDGE_NETWORK_ENABLED | No | Enable network retrieval tool: 'true' or 'false' | false |
| GLM_BRIDGE_REMOTE_AUTH_MODE | No | Remote authentication mode: 'none', 'bearer', or 'oauth_metadata' | |
| GLM_BRIDGE_REMOTE_AUTH_TOKEN | No | Bearer token for remote authentication when using 'bearer' mode |
Capabilities
Features and capabilities supported by this server
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
| prompts | {
"listChanged": true
} |
| resources | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| glm_5_route_agentic_taskB | Delegate multi-step planning, implementation proposals, debugging, migrations, or refactors to GLM; it proposes but never executes host tools. |
| glm_5_query_reasoningC | Resolve a difficult technical, systems, debugging, algorithmic, mathematical, or architecture bottleneck with provider-supported reasoning. |
| glm_5_consult_knowledgeB | Consult GLM for an independent expert explanation, second opinion, architecture advice, or unfamiliar concept—not task execution. |
| glm_5v_diff_ui_layoutC | Audit a local PNG, JPEG, JPG, or WEBP screenshot, mockup, or wireframe against an objective using the vision model. |
| glm_5_context_manageB | Create, update, retrieve, list, or delete reusable local project contexts. Contexts never include API keys. |
| glm_5_inspect_project_contextA | Safely inspect an approved local project directory with read-only bounded file metadata, tree, package, and Git-summary information. |
| glm_5_run_controlled_agentB | Run a bounded, read-only GLM tool-use loop within an approved directory. It cannot write files or run arbitrary commands. |
| glm_5_smart_routeC | Deterministically route a request to vision, agentic planning, reasoning, or knowledge consultation without recursive MCP calls. |
| glm_5_continue_taskB | Continue a persisted agentic task using its objective and compact prior summary. It proposes only and does not execute host tools. |
| glm_5_propose_changesA | Create a persistent, reviewable file-change proposal. This never mutates files or executes commands; explicit matching approval is required for application. |
| glm_5_approve_and_apply_changesB | Apply an explicitly approved proposal's scoped file operations, create a rollback checkpoint, and record an audit entry. Commands are not executed. |
| glm_5_rollback_changesA | Restore a proposal checkpoint after an explicit matching approval token. Only restores files in the proposal's working directory. |
| glm_5_reissue_approvalB | Reissue a fresh approval ID for the current proposal revision, revoking the previous approval token. |
| glm_5_revoke_approvalB | Revoke the current approval token for a proposal without applying mutation. |
| glm_5_plan_code_changeB | Plan an approval-gated code change and persist the proposed file operations without mutating the repository. |
| glm_5_propose_patchA | Propose a scoped patch as reviewable file operations. No files are changed until a later exact approval. |
| glm_5_apply_approved_patchC | Apply an explicitly approved proposed patch and create a rollback checkpoint. |
| glm_5_review_change_setA | Inspect a proposed change set together with its audit trail before approval or rollback. |
| glm_5_rollback_change_setC | Roll back an applied change set by restoring its checkpoint inside the approved working directory. |
| glm_5_run_approved_commandB | Run an allowlisted project validation command after explicit matching approval. Arbitrary shell execution is not supported. |
| glm_5_execute_development_taskC | Create an auditable development orchestration plan using the safe development workflow surface. No mutation occurs automatically. |
| glm_5_orchestrate_project_taskC | Create an auditable role-specific, dependency-aware development plan/job. It never mutates files without a separate explicit approval workflow. |
| glm_5_inspect_jobC | Inspect a persisted orchestration job and its safe task graph status. |
| glm_5_resume_jobC | Resume a non-mutating job planning state; mutation remains approval-gated. |
| glm_5_cancel_jobC | Cancel future work in a persisted job while preserving audit state. |
| glm_5_manage_policy_profileC | Inspect or upsert auditable policy profiles that control writes, commands, network access, and privacy posture. |
| glm_5_inspect_repository_memoryB | List or inspect persisted repository memory entries with provenance, confidence, and status metadata. |
| glm_5_update_repository_memoryB | Create or update repository memory entries. Confirmed facts require explicit provenance; inference must remain marked accordingly. |
| glm_5_create_workflowA | Create a reusable local workflow definition with validated step dependencies and bounded step types. |
| glm_5_run_workflowC | Instantiate a reusable workflow as an auditable planning job. It can optionally execute approved command-backed quality gates. |
| glm_5_list_pending_approvalsA | List pending change proposals that still require an exact matching approval before mutation or approved commands. |
| glm_5_inspect_workspaceA | Inspect a repository or monorepo root for workspace signals, package manifests, and package layout metadata. |
| glm_5_compare_model_recommendationsC | Compare a reasoning-oriented GLM answer with an independent knowledge-oriented answer for the same question. |
| glm_5_evaluate_model_routingC | Score likely routing modes for a request without executing the routed tool. |
| glm_5_fetch_referenceC | Fetch an external HTTPS reference only when network retrieval is enabled and the target domain is allowlisted. |
| glm_5_export_project_stateC | Export safe persisted bridge state such as workflows, policies, repository memory, and job summaries without secrets or raw source files. |
| glm_5_import_project_stateC | Import safe persisted bridge state from a validated payload. Dry-run is enabled by default. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| glm_architecture_review | Prepare an architecture review routed to GLM reasoning. |
| glm_repository_audit | Prepare a safe repository audit using read-only inspection. |
| glm_debugging_session | Prepare a focused debugging consultation. |
| glm_ui_review | Prepare a visual UI review. |
| glm_second_opinion | Prepare an independent technical second opinion. |
| glm_implementation_task | Prepare a constrained implementation planning request. |
| glm_safe_refactor | Prepare a safe refactor request with explicit approval boundaries. |
| glm_fix_failing_tests | Prepare a failing-test investigation and patch-planning session. |
| glm_dependency_upgrade | Prepare a dependency-upgrade workflow with scoped approval expectations. |
| glm_multi_agent_implementation | Prepare a role-coordinated implementation planning request. |
| glm_repository_modernization | Prepare a repository modernization audit and workflow plan. |
| glm_security_remediation | Prepare a security remediation workflow without implying unrestricted autonomy. |
| glm_release_readiness | Prepare a release-readiness assessment. |
| glm_architecture_consensus | Prepare a consensus-style architecture comparison between reasoning and knowledge tools. |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| capabilities | Selected provider capabilities and server policy |
| configuration | Sanitized bridge configuration |
| health | Current runtime health and registration summary |
| contexts | Stored context metadata |
| sessions | Stored task session metadata |
| jobs | Persisted orchestration and workflow jobs |
| workflows | Available built-in and custom workflow definitions |
| policies | Available policy profiles |
| approvals | Pending approval-gated development approvals |
| repository-memory | Long-term repository memory entries |
| evaluations | Current provider and routing evaluation summary |
| audit | Safe development audit log entries |
| evidence | Recorded evidence for quality gates, command outputs, and other safe conclusions |
| Dependency Upgrade | A single workflow definition |
| Documentation Refresh | A single workflow definition |
| Fix Failing Tests | A single workflow definition |
| Release Readiness | A single workflow definition |
| Repository Audit | A single workflow definition |
| Safe Refactor | A single workflow definition |
| Security Remediation | A single workflow definition |
| UI Quality Review | A single workflow definition |
| dependency_maintenance | A single policy profile |
| read_only | A single policy profile |
| safe_development | A single policy profile |
| strict_enterprise | A single policy profile |
| ui_review | A single policy profile |
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/Magnexis/LLM-bridge-mcp-server'
If you have feedback or need assistance with the MCP directory API, please join our Discord server