Skip to content

Commit 46894fd

Browse files
mdlmarkhammdlmarkham
committed
feat: add new configuration files for Local Ollama Assistant and MCP server, enhance agent documentation, and update remote MCP testing session
1 parent 287d85e commit 46894fd

File tree

7 files changed

+183
-0
lines changed

7 files changed

+183
-0
lines changed

‎.continue/agents/new-config.yaml‎

Lines changed: 33 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,33 @@
1+
name: Local Ollama Assistant
2+
version: 0.0.1
3+
schema: v1
4+
5+
models:
6+
# Main coding/chat model
7+
- name: deepseek-v3.1:671b-cloud
8+
provider: ollama
9+
model: deepseek-v3.1:671b-cloud # must match `ollama list`
10+
apiBase: http://100.111.84.5:11434 # your remote Ollama host
11+
roles:
12+
- chat
13+
- edit
14+
- autocomplete
15+
- apply
16+
- summarize
17+
18+
# Embedding model for codebase search / RAG
19+
- name: embeddingsProvider
20+
provider: ollama
21+
model: nomic-embed-text # `ollama pull nomic-embed-text`
22+
roles:
23+
- embed
24+
25+
# What context the assistant can see
26+
context:
27+
- provider: code
28+
- provider: docs
29+
- provider: diff
30+
- provider: terminal
31+
- provider: problems
32+
- provider: folder
33+
- provider: codebase

‎.continue/mcpServers/new-mcp-server.yaml‎

Lines changed: 10 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,10 @@
1+
name: New MCP server
2+
version: 0.0.1
3+
schema: v1
4+
mcpServers:
5+
- name: New MCP server
6+
command: npx
7+
args:
8+
- -y
9+
- <your-mcp-server>
10+
env: {}

‎.github/agents/007.agent.md‎

Lines changed: 5 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,5 @@
1+
---
2+
description: 'Test Agent'
3+
tools: ['search', 'testFailure', 'todos']
4+
---
5+
Define what this custom agent accomplishes for the user, when to use it, and the edges it won't cross. Specify its ideal inputs/outputs, the tools it may call, and how it reports progress or asks for help.

‎.roo/mcp.json‎

Lines changed: 8 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,8 @@
1+
{
2+
"mcpServers": {
3+
"context7": {
4+
"type": "streamable-http",
5+
"url": "https://mcp.context7.com/mcp"
6+
}
7+
}
8+
}

‎.roomodes‎

Lines changed: 48 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,48 @@
1+
customModes:
2+
- slug: project-research
3+
name: 🔍 Project Research
4+
roleDefinition: |
5+
You are a detailed-oriented research assistant specializing in examining and understanding codebases. Your primary responsibility is to analyze the file structure, content, and dependencies of a given project to provide comprehensive context relevant to specific user queries.
6+
whenToUse: |
7+
Use this mode when you need to thoroughly investigate and understand a codebase structure, analyze project architecture, or gather comprehensive context about existing implementations. Ideal for onboarding to new projects, understanding complex codebases, or researching how specific features are implemented across the project.
8+
description: Investigate and analyze codebase structure
9+
groups:
10+
- read
11+
source: project
12+
customInstructions: |
13+
Your role is to deeply investigate and summarize the structure and implementation details of the project codebase. To achieve this effectively, you must:
14+
15+
1. Start by carefully examining the file structure of the entire project, with a particular emphasis on files located within the "docs" folder. These files typically contain crucial context, architectural explanations, and usage guidelines.
16+
17+
2. When given a specific query, systematically identify and gather all relevant context from:
18+
- Documentation files in the "docs" folder that provide background information, specifications, or architectural insights.
19+
- Relevant type definitions and interfaces, explicitly citing their exact location (file path and line number) within the source code.
20+
- Implementations directly related to the query, clearly noting their file locations and providing concise yet comprehensive summaries of how they function.
21+
- Important dependencies, libraries, or modules involved in the implementation, including their usage context and significance to the query.
22+
23+
3. Deliver a structured, detailed report that clearly outlines:
24+
- An overview of relevant documentation insights.
25+
- Specific type definitions and their exact locations.
26+
- Relevant implementations, including file paths, functions or methods involved, and a brief explanation of their roles.
27+
- Critical dependencies and their roles in relation to the query.
28+
29+
4. Always cite precise file paths, function names, and line numbers to enhance clarity and ease of navigation.
30+
31+
5. Organize your findings in logical sections, making it straightforward for the user to understand the project's structure and implementation status relevant to their request.
32+
33+
6. Ensure your response directly addresses the user's query and helps them fully grasp the relevant aspects of the project's current state.
34+
35+
These specific instructions supersede any conflicting general instructions you might otherwise follow. Your detailed report should enable effective decision-making and next steps within the overall workflow.
36+
- slug: security-review
37+
name: 🛡️ Security Reviewer
38+
roleDefinition: |
39+
You perform static and dynamic audits to ensure secure code practices. You flag secrets, poor modular boundaries, and oversized files.
40+
whenToUse: |
41+
Use this mode when you need to audit code for security vulnerabilities, review code for security best practices, or identify potential security risks. Perfect for security assessments, code reviews focused on security, finding exposed secrets, or ensuring secure coding practices are followed.
42+
description: Audit code for security vulnerabilities
43+
groups:
44+
- read
45+
- edit
46+
source: project
47+
customInstructions: |
48+
Scan for exposed secrets, env leaks, and monoliths. Recommend mitigations or refactors to reduce risk. Flag files > 500 lines or direct environment coupling. Use `new_task` to assign sub-audits. Finalize findings with `attempt_completion`.

‎logs/audit.log‎

Lines changed: 12 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -87,3 +87,15 @@
8787
{"timestamp":"2025-11-16T02:57:30.956842Z","tool":"get_stack_network_info","subject":null,"args":{"host":"node-1","stack_name":"webapp"},"result_status":"success","error":null,"truncated":false,"dry_run":false}
8888
{"timestamp":"2025-11-16T02:57:30.960223Z","tool":"get_stack_network_info","subject":null,"args":{"host":"node-1","stack_name":"webapp"},"result_status":"success","error":null,"truncated":false,"dry_run":false,"tailscale":{"tailscale_node":"Desktop","tailscale_user":4381597146989997,"tailscale_tags":[],"tailnet":"tailf9480.ts.net"}}
8989
{"timestamp":"2025-11-16T02:57:30.984729Z","tool":"get_stack_network_info","subject":null,"args":{"host":"node-1","stack_name":"webapp"},"result_status":"success","error":null,"truncated":false,"dry_run":false,"tailscale":{"tailscale_node":"Desktop","tailscale_user":4381597146989997,"tailscale_tags":[],"tailnet":"tailf9480.ts.net"}}
90+
{"timestamp":"2025-11-18T03:32:29.465126Z","tool":"get_stack_network_info","subject":null,"args":{"host":"node-1","stack_name":"webapp"},"result_status":"success","error":null,"truncated":false,"dry_run":false}
91+
{"timestamp":"2025-11-18T03:32:29.498993Z","tool":"get_stack_network_info","subject":null,"args":{"host":"node-1","stack_name":"webapp"},"result_status":"success","error":null,"truncated":false,"dry_run":false}
92+
{"timestamp":"2025-11-18T03:32:29.502912Z","tool":"get_stack_network_info","subject":null,"args":{"host":"node-1","stack_name":"webapp"},"result_status":"success","error":null,"truncated":false,"dry_run":false,"tailscale":{"tailscale_node":"Desktop","tailscale_user":4381597146989997,"tailscale_tags":[],"tailnet":"tailf9480.ts.net"}}
93+
{"timestamp":"2025-11-18T03:32:29.530603Z","tool":"get_stack_network_info","subject":null,"args":{"host":"node-1","stack_name":"webapp"},"result_status":"success","error":null,"truncated":false,"dry_run":false,"tailscale":{"tailscale_node":"Desktop","tailscale_user":4381597146989997,"tailscale_tags":[],"tailnet":"tailf9480.ts.net"}}
94+
{"timestamp":"2025-11-18T03:33:45.246813Z","tool":"get_stack_network_info","subject":null,"args":{"host":"node-1","stack_name":"webapp"},"result_status":"success","error":null,"truncated":false,"dry_run":false}
95+
{"timestamp":"2025-11-18T03:33:45.258614Z","tool":"get_stack_network_info","subject":null,"args":{"host":"node-1","stack_name":"webapp"},"result_status":"success","error":null,"truncated":false,"dry_run":false}
96+
{"timestamp":"2025-11-18T03:33:45.262419Z","tool":"get_stack_network_info","subject":null,"args":{"host":"node-1","stack_name":"webapp"},"result_status":"success","error":null,"truncated":false,"dry_run":false,"tailscale":{"tailscale_node":"Desktop","tailscale_user":4381597146989997,"tailscale_tags":[],"tailnet":"tailf9480.ts.net"}}
97+
{"timestamp":"2025-11-18T03:33:45.289542Z","tool":"get_stack_network_info","subject":null,"args":{"host":"node-1","stack_name":"webapp"},"result_status":"success","error":null,"truncated":false,"dry_run":false,"tailscale":{"tailscale_node":"Desktop","tailscale_user":4381597146989997,"tailscale_tags":[],"tailnet":"tailf9480.ts.net"}}
98+
{"timestamp":"2025-11-18T03:33:57.608352Z","tool":"get_stack_network_info","subject":null,"args":{"host":"node-1","stack_name":"webapp"},"result_status":"success","error":null,"truncated":false,"dry_run":false}
99+
{"timestamp":"2025-11-18T03:33:57.619489Z","tool":"get_stack_network_info","subject":null,"args":{"host":"node-1","stack_name":"webapp"},"result_status":"success","error":null,"truncated":false,"dry_run":false}
100+
{"timestamp":"2025-11-18T03:33:57.622858Z","tool":"get_stack_network_info","subject":null,"args":{"host":"node-1","stack_name":"webapp"},"result_status":"success","error":null,"truncated":false,"dry_run":false,"tailscale":{"tailscale_node":"Desktop","tailscale_user":4381597146989997,"tailscale_tags":[],"tailnet":"tailf9480.ts.net"}}
101+
{"timestamp":"2025-11-18T03:33:57.648437Z","tool":"get_stack_network_info","subject":null,"args":{"host":"node-1","stack_name":"webapp"},"result_status":"success","error":null,"truncated":false,"dry_run":false,"tailscale":{"tailscale_node":"Desktop","tailscale_user":4381597146989997,"tailscale_tags":[],"tailnet":"tailf9480.ts.net"}}

‎test_remote_mcp.md‎

Lines changed: 67 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,67 @@
1+
# Remote MCP Testing Session - dev1
2+
3+
## Server Status
4+
- **URL**: http://dev1.tailf9480.ts.net:8080/mcp
5+
- **Status**: ✅ Running (PID 7790)
6+
- **Deployment**: Latest code from origin/master (commit e9bc08e)
7+
8+
## Test Plan
9+
10+
### 1. System Monitoring Tools
11+
- [ ] get_system_status - Get CPU, memory, disk usage
12+
- [ ] get_process_list - List running processes
13+
- [ ] get_disk_info - Detailed disk information
14+
- [ ] analyze_system_health - AI-powered health analysis
15+
16+
### 2. Docker Container Tools
17+
- [ ] get_container_list - List all containers
18+
- [ ] get_container_logs - Get container logs
19+
- [ ] manage_container - Start/stop/restart containers
20+
- [ ] inspect_container - Detailed container info
21+
- [ ] get_container_stats - Real-time container stats
22+
23+
### 3. Network Tools
24+
- [ ] get_network_status - Network interfaces and stats
25+
- [ ] check_connectivity - Test network connectivity
26+
- [ ] get_port_info - Check listening ports
27+
- [ ] trace_route - Trace route to destination
28+
- [ ] get_dns_info - DNS lookup
29+
30+
### 4. File Operations
31+
- [ ] read_file - Read file contents
32+
- [ ] search_files - Search for files
33+
- [ ] analyze_logs - AI-powered log analysis
34+
35+
### 5. Stack Management
36+
- [ ] get_stack_status - Docker Compose stack status
37+
- [ ] get_stack_network_info - Stack network configuration
38+
- [ ] deploy_stack - Deploy/update stacks
39+
40+
### 6. Inventory Tools
41+
- [ ] list_applications - List detected applications
42+
- [ ] get_application_info - Application details
43+
- [ ] update_inventory - Refresh inventory
44+
- [ ] export_inventory - Export inventory data
45+
46+
### 7. Admin Tools
47+
- [ ] execute_command - Run system commands (high-risk)
48+
- [ ] manage_service - Systemd service control
49+
50+
### 8. Image Management
51+
- [ ] list_images - List Docker images
52+
- [ ] pull_image - Pull new images
53+
- [ ] remove_image - Remove images
54+
55+
## Test Execution
56+
57+
Use the SystemManager-HTTP MCP connection in GitHub Copilot Chat to test these tools.
58+
59+
**Connected via**: VSCode MCP extension → SystemManager-HTTP → dev1.tailf9480.ts.net:8080/mcp
60+
61+
---
62+
63+
## Notes
64+
- Server deployed with token authentication
65+
- Running on Python 3.12.3
66+
- Using FastMCP 2.13.1
67+
- All dependencies installed successfully

0 commit comments

Comments
 (0)