Das standardmäßige sequential-thinking MCP bietet ein großartiges Werkzeug für Chain-of-Thought-Überlegungen, leidet jedoch unter dem „Stille-Post“-Problem in Multi-Agenten-Umgebungen, bei denen Agenten selbstbewusst unbegründete Gedanken halluzinieren können, die das Kontextfenster vergiften.
krusch-sequential-mcp löst dies durch die Einführung eines semantischen Plausibilitäts-Gatings zusammen mit einer hochzuverlässigen DBOS PostgreSQL-Persistenzschicht.
🧠 Semantisches Plausibilitäts-Gating: Erkennt und verwirft autonom abgedriftete oder halluzinierte Gedanken über einen Edge-Modell-Evaluator.
💾 DBOS PostgreSQL-Persistenz: Speichert jeden Gedanken, Zweig und jede Revision synchron in einer dbos_thoughts-Tabelle und erstellt so einen prüfbaren DAG der Argumentation.
🛑 Deterministische Zustandszuverlässigkeit: Stoppt die Ausführung vergifteter Gedanken und zwingt Agenten dazu, ihren Argumentationspfad neu zu bewerten.
🔌 Drop-In-Ersatz: Vollständig kompatibel mit der standardmäßigen sequential-thinking-Schnittstelle bei gleichzeitiger Unterstützung des neuen groundingContext-Parameters.
📦 Keine externen Abhängigkeiten: Der Plausibilitäts-Evaluator ist vollständig in sich geschlossen – kein externes Toolkit erforderlich.
Related MCP server: Tyra Advanced Memory MCP Server
Wenn ein Agent einen Gedanken vorschlägt, prüft der interne Evaluator diesen anhand des bereitgestellten groundingContext.
graph TD;
A[Agent Thought Proposed] --> B{Grounding Context Provided?};
B -- No --> C[Accept & Persist to DBOS];
B -- Yes --> D[Edge Model Evaluator];
D -- Plausible --> C;
D -- Hallucinated/Drifted --> E[Reject Thought];
E --> F[Return Soft Error to Agent];
F --> G[Agent Re-evaluates];npm install -g krusch-sequential-mcpOder konfigurieren Sie es in Ihrer MCP-Einstellungsdatei (z. B. claude_desktop_config.json oder .cursor/mcp.json):
{
"mcpServers": {
"krusch-sequential-mcp": {
"command": "npx",
"args": ["-y", "krusch-sequential-mcp"]
}
}
}Agenten können das sequentialthinking-Tool mit den Standardparametern (thought, thoughtNumber, totalThoughts, nextThoughtNeeded usw.) aufrufen.
Um das Plausibilitäts-Gate zu aktivieren, fügen Sie den groundingContext-Parameter in Ihren Tool-Aufruf ein:
{
"thought": "Since the user is asking about the database schema, I will assume it uses MongoDB and write a query for it.",
"thoughtNumber": 1,
"totalThoughts": 3,
"nextThoughtNeeded": true,
"groundingContext": "The current codebase exclusively uses DBOS PostgreSQL for persistence. No NoSQL databases are present."
}Da der Gedanke im Widerspruch zum groundingContext steht, wird der Evaluator ihn autonom ablehnen und einen Fehler an den Agenten zurückgeben, damit dieser seinen Ansatz überdenkt.
Variable | Erforderlich | Standard | Beschreibung |
| Nein | (keine — Persistenz deaktiviert) | PostgreSQL-Verbindungszeichenfolge (z. B. |
| Nein |
| Basis-URL zum Ollama-Dienst für Plausibilitätsprüfungen. |
| Nein |
| Ollama-Modell, das für das Plausibilitäts-Screening verwendet wird. Sollte ein kleines, schnelles Modell sein. |
Kopieren Sie .env.example für einen schnellen Start:
cp .env.example .envWir freuen uns über Beiträge! Bitte stellen Sie sicher, dass Ihre Tests bestehen und die Formatierungsstandards des Projekts eingehalten werden.
Führen Sie Tests über npm run build und npm start (oder node build/index.js) aus.
MIT-Lizenz © 2026 kruschdev
A detailed tool for dynamic and reflective problem-solving through thoughts. Augmented with Semantic Plausibility Gating.
| Name | Required | Description | Default |
|---|---|---|---|
| thought | Yes | Your current thinking step | |
| branchId | No | Branch identifier | |
| isRevision | No | Whether this revises previous thinking | |
| thoughtNumber | Yes | Current thought number | |
| totalThoughts | Yes | Estimated total thoughts needed | |
| revisesThought | No | Which thought is being reconsidered | |
| groundingContext | No | OPTIONAL: Provide the source context for this thought. The server will independently verify the plausibility of your thought against this context. | |
| branchFromThought | No | Branching point thought number | |
| needsMoreThoughts | No | If more thoughts are needed | |
| nextThoughtNeeded | Yes | Whether another thought step is needed |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations exist, so the description carries the full burden. It mentions 'Semantic Plausibility Gating' which hints at a verification mechanism, but does not explain how it works, what data is stored, or any side effects. The schema's groundingContext field description provides some behavior, but the main description is insufficient for an agent to understand the tool's operational characteristics.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is very short at one sentence, which is lean but not necessarily well-structured. It front-loads the core concept, but the single sentence lacks detail that could be organized in a more informative way. It is not overly verbose, but it doesn't make effective use of its brevity.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a complex tool with 10 parameters and no output schema, the description is inadequate. It doesn't explain the workflow (e.g., how to sequence thoughts, the meaning of branchId, revision, nextThoughtNeeded), nor does it describe the plausibility gating behavior beyond naming it. The schema helps but the description leaves the agent without context on how to use the tool effectively.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
All 10 parameters have schema descriptions, so the baseline is 3. The main description adds no parameter-specific meaning, and it doesn't mention any relationships between params. However, given 100% schema coverage, the schema itself is sufficient for understanding parameters.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description describes the tool as 'for dynamic and reflective problem-solving through thoughts', which conveys the general domain but lacks a specific action verb (e.g., submit, record) or resource. The name 'sequentialthinking' partially compensates, but the description alone doesn't clarify what the tool does beyond generic problem-solving.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus other tools. No alternatives are mentioned, and no context is provided about the appropriate use case. The description simply states what it is without indications of when it should be preferred.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v1.0.0sequentialthinkingScored across 1 tool
Only one tool exists, so there is no possibility of confusion or overlap. The tool's purpose is singular and clear.
With a single tool, naming consistency is trivially satisfied. The name 'sequentialthinking' is descriptive and matches the server's focus.
The server has exactly one tool, which feels minimal. While it is appropriate for a focused sequential thinking utility, the count is on the borderline of being too thin.
The tool appears to provide a comprehensive capability for sequential thinking and problem-solving. However, being the only tool, there may be missing auxiliary operations like reset or history, though no obvious gaps are evident.
Cloud-hosted MCP server for durable AI memory
Hosted MCP server connecting claude.ai, ChatGPT and other AI apps to your own computer
MCP server for AI dialogue using various LLM models via AceDataCloud
Capability registry for the agentic economy. Semantic search over verified MCP server listings.
