UltimateBLOCK
Comprehensive MCP server exposing dozens of capabilities to AI agents: multi-provider LLM delegation, browser automation, document processing, vector ops, and cognitive memory systems
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
[](https://www.python.org/downloads/) [](./LICENSE) [](https://github.com/modelcontextprotocol)
A comprehensive Model Context Protocol (MCP) server providing advanced AI agents with dozens of powerful capabilities for cognitive augmentation, tool use, and intelligent orchestration
Getting Started • Key Features • Usage Examples • Architecture
🤖 What is Ultimate MCP Server?
Ultimate MCP Server is a comprehensive MCP-native system that serves as a complete AI agent operating system. It exposes dozens of powerful capabilities through the Model Context Protocol, enabling advanced AI agents to access a rich ecosystem of tools, cognitive systems, and specialized services.
While it includes intelligent task delegation from sophisticated models (e.g., Claude 3.7 Sonnet) to cost-effective ones (e.g., Gemini Flash 2.0 Lite), this is just one facet of its extensive functionality. The server provides unified access to multiple LLM providers while optimizing for cost, performance, and quality.
The system offers integrated cognitive memory systems, browser automation, Excel manipulation, database interactions, document processing, command-line utilities, dynamic API integration, OCR capabilities, vector operations, entity relation graphs, SQL database interactions, audio transcription, and much more. These capabilities transform an AI agent from a conversational interface into a powerful autonomous system capable of complex, multi-step
37b43ada8923OBSERVED · 2026-10-07Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add ultimate_mcp_server --env TIKTOKEN_ENCODING=${TIKTOKEN_ENCODING} --env VAULT_TOKEN=${VAULT_TOKEN} -- uvx ultimate_mcp_server{
"mcpServers": {
"ultimate_mcp_server": {
"command": "uvx",
"args": [
"ultimate_mcp_server"
],
"env": {
"TIKTOKEN_ENCODING": "${TIKTOKEN_ENCODING}",
"VAULT_TOKEN": "${VAULT_TOKEN}"
}
}
}
}Exposed tools (1)
0 read · 1 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
execute_workflow | write | Execute a multi-step workflow by calling registered project tools. |
Trust audit
BLOCKgrade F · trust 55/100 Do not install this without reading the findings. The audit found something that could harm you or your machine.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | WARN |
| L1 | Static analysis of the code | FAIL |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (6 observation(s))
- Network
- declared (3 observation(s))
- Shell
- declared (4 observation(s))
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (25)
self._in_memory_store[namespace] = pickle.loads(data)
loaded_cache = pickle.load(f)
data = pickle.load(f)
cache_data = pickle.loads(data)
locator_cache.db
return random.choice([12345, True, None, ["list"], {"key": "val"}])nonce = random.randint(1000, 9999) # Simple nonce/cache buster
"autopilot_run": "🧑✈️",
"autopilot_critical_error": "💥🧑✈️",
.cursorignore
.envrc
examples/sample/contract_link.txt
return hashlib.md5(significant_words.encode("utf-8")).hexdigest()return f"semantic:{hashlib.md5(words_key.encode('utf-8')).hexdigest()}"params_hash = hashlib.md5(params_str.encode()).hexdigest()
text_hash = hashlib.md5(text.encode("utf-8")).hexdigest()return hashlib.sha1(txt.encode("utf-8", "ignore")).hexdigest()"../../etc/passwd"
INFO: Uvicorn running on http://0.0.0.0:9000 (Press CTRL+C to quit)
proxy_pass http://127.0.0.1:8013/; # Point to the internal server (note trailing /)
- `http://127.0.0.1:8013/mcp` - Main MCP streamable-HTTP endpoint
- `http://127.0.0.1:8013/` - Discovery endpoint
- `http://127.0.0.1:8013/api/health` - Health check
img_bytes = base64.b64decode(image_data)
image_bytes = base64.b64decode(image_data)
Gates applied: no_behavioural_pass.
37b43ada8923full audit observations/trust-audit/mcp-server/dicklesworthstone__ultimate.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-07 | 37b43ada8923 | BLOCK | F | 55 | first audit |
Questions
What is the Ultimate MCP server?
Comprehensive MCP server exposing dozens of capabilities to AI agents: multi-provider LLM delegation, browser automation, document processing, vector ops, and cognitive memory systems
What tools does Ultimate expose?
1 in total: 0 read-only, 1 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is Ultimate safe to connect to an agent?
No — not without reading the findings first. The audit graded it F (55/100) and found 4 critical or high issues in the source. Each one is listed on this page with the file and line it is on.
What credentials does Ultimate need?
It reads TIKTOKEN_ENCODING and VAULT_TOKEN from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does Ultimate run?
It speaks sse, stdio and streamable-http, so it runs as a local process your client starts. It is published on PyPI as ultimate_mcp_server.
How current is this page?
The grade is for one exact copy of the source (37b43ada8923), read on 2026-10-07. The repository is watched and re-audited when it changes.