How do I use mcp-research-collective?

1. Click on "Install Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@mcp-research-collective What is the role of a Faculty Senate and why have one?" That's it! The server will respond to your query, and you can continue using it as needed. Here is a step-by-step guide with screenshots.

de en es ja ko ru zh

mcp-research-collective

by SiegKat

Overview Schema Related Servers Score Discussions

Local

mcp-research-collective

A multi-agent research system built on the Model Context Protocol (MCP). Specialized agents (Planner → Researcher → Reasoner) collaborate via a thread-safe blackboard of shared beliefs, exposed as MCP tools that can be wired into Claude Desktop or any other MCP host.

Python License Local-first MCP Async

What this demonstrates

Model Context Protocol — a real, runnable FastMCP server with seven tools (blackboard_set, blackboard_get, blackboard_query, blackboard_dump, plus add/subtract/multiply/divide).
Blackboard architecture — a thread-safe shared belief store (Belief dataclass + Blackboard class with RLock-protected upsert/read/query, TTLs, regex queries, and tag filters).
Multi-agent orchestration — Planner decomposes the prompt → Researcher fetches facts from a JSON KB → Reasoner synthesizes the final answer. Agents only know about the connector, never each other; they coordinate solely through the blackboard.
Two interchangeable transports — an in-process MCPConnector for fast notebook/test runs, and the actual STDIO FastMCP server for production / Claude Desktop integration.

Related MCP server: AI Blog MCP Agent

Tech stack

Model Context Protocol Python SDK (mcp[cli]) — FastMCP server, ClientSession, STDIO transport
Python 3.10+, asyncio, threading.RLock
pytest for deterministic blackboard / agent tests
No LLM dependency — the agents in this demo orchestrate over a structured KB. The MCP server is the surface that you (or any MCP host) can attach an LLM to.

Architecture

flowchart TB
    U[User Prompt] --> P[PlannerAgent<br/>decomposes into subtasks]
    P -->|publishes 'task.list'| BB[(Blackboard<br/>thread-safe<br/>belief store)]
    BB -->|reads tasks| R[ResearchAgent<br/>fetches from kb/*.json]
    R -->|publishes belief.what / why / how| BB
    BB -->|reads beliefs| S[ReasonerAgent<br/>synthesizes answer]
    S -->|publishes answer.v1| BB
    S --> Out[Final answer<br/>+ full blackboard state]

    subgraph "MCP Surface"
        BB <-->|set/get/query/dump| MCP[FastMCP server<br/>STDIO transport]
        MCP <-->|JSON-RPC| Claude[Claude Desktop /<br/>any MCP host]
    end

Quickstart

# 1. Python env
python -m venv .venv
source .venv/Scripts/activate   # Windows: .venv\Scripts\activate
pip install -e .[dev]

# 2. Run the deterministic tests
pytest

# 3. Run the in-process orchestrator from the CLI
mcp-research-orchestrator "What is a Faculty Senate, why have one, and how is it built?"

# 4. Run the standalone MCP server (for Claude Desktop or another MCP host)
mcp-research-collective

Programmatic usage (in-process, no STDIO)

from mcp_research_collective import run_collective

answer, blackboard_state_json = run_collective(
    "What is the role of a Faculty Senate and why have one?"
)

print(answer)
# # Synthesized Answer
#
# **What it is**
# - Elected body of faculty that represents the academic community...
# ...
# **Why it matters**
# - Ensures academic decisions are not solely administrative
# ...

Use with Claude Desktop

This is the differentiator: the same code that runs the in-process demo is also a working MCP server you can connect to Claude Desktop. Add this to your claude_desktop_config.json:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "research-collective": {
      "command": "python",
      "args": ["-m", "mcp_research_collective.entrypoints.run_server"],
      "env": {
        "PYTHONPATH": "/absolute/path/to/mcp-research-collective/src"
      }
    }
  }
}

After restarting Claude Desktop, you'll see four blackboard_* tools and four math tools available in the Claude UI. Try:

Use the blackboard_set tool to publish a fact about my project deadline, then blackboard_query to find it back.

Adding a new research topic

Drop a JSON file in src/mcp_research_collective/kb/ with the schema:

{
  "key": "topic.subkey",
  "what": ["fact 1", "fact 2"],
  "why":  ["fact 1", "fact 2"],
  "how":  ["fact 1", "fact 2"]
}

Then construct the orchestrator with topic_key="topic.subkey". No code changes required.

What I learned

The Planner→Researcher→Reasoner pattern with a blackboard makes each agent's responsibility small enough to reason about in isolation. The system dynamically scales its effort based on the prompt: asking only "what" and "why" results in the Planner publishing only define.what and explain.why. The Researcher fetches exactly what is needed, and the blackboard tracks this selective context gathering.

The biggest win wasn't the MCP wire format — it was the discipline of forcing every state mutation through mcp.call("blackboard.set", ...). That single chokepoint makes the whole system trivially observable: dump_state() shows exactly what each agent contributed, when, and with what confidence. Adding a fourth agent (like a Critic or a Cache) is straightforward because the contract is simply "read tagged beliefs, write tagged beliefs."

Project layout

mcp-research-collective/
├── src/mcp_research_collective/
│   ├── blackboard.py        # Belief + thread-safe Blackboard
│   ├── connector.py         # In-process MCPConnector (set/get/query/dump)
│   ├── kb/*.json            # Knowledge base topics (drop-in JSON files)
│   ├── knowledge_base.py    # Loader for kb/*.json
│   ├── agents.py            # PlannerAgent, ResearchAgent, ReasonerAgent
│   ├── orchestrator.py      # CollectiveOrchestrator + run_collective
│   ├── mcp_server.py        # FastMCP server exposing blackboard + math tools
│   └── entrypoints/
│       ├── run_server.py        # `python -m ... run_server`
│       └── run_orchestrator.py  # `python -m ... run_orchestrator "<q>"`
├── tests/                   # blackboard + connector + orchestrator + KB tests
└── notebooks/demo.ipynb     # walkthrough with full blackboard state dump

Available Tools

8 tools

addB

Sum two numbers.

ParametersJSON Schema

Name	Required	Description	Default
`a`	Yes
`b`	Yes

Output Schema

ParametersJSON Schema

Name	Required	Description
`result`	Yes

TDQS

B3.4/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description discloses the basic behavior of adding two numbers, which is sufficient for such a simple operation. Since no annotations are provided, the description carries the full burden, and it is clear and transparent.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is extremely concise, consisting of a single sentence. Every word is purposeful, and there is no extraneous information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple arithmetic tool with an output schema, the description provides the essential information. However, it lacks guidance on edge cases, precision, or return value details, which could be beneficial.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters1/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The description 'Sum two numbers.' does not add any meaning to the parameters a and b beyond the input schema. With 0% schema description coverage, the description should compensate, but it fails to elaborate on what the parameters represent.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description 'Sum two numbers.' clearly states the action (sum) and the resource (two numbers). It distinguishes this tool from sibling arithmetic operations like divide, multiply, and subtract.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided on when to use this tool versus alternatives. The description does not mention any conditions, prerequisites, or scenarios where addition is preferred.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

blackboard_dumpA

Return the full (non-expired) blackboard state.

ParametersJSON Schema

Name	Required	Description	Default
No parameters

Output Schema

ParametersJSON Schema

Name	Required	Description
No output parameters

TDQS

A3.7/5.0

Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description mentions 'non-expired', indicating that expired entries are excluded, which is a behavioral detail. However, with no annotations, it lacks disclosure of side effects, performance implications, or whether it's a snapshot. More context would improve transparency.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence with 6 words, very concise and directly to the point. No wasted words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description is minimal but covers the essential purpose. However, the tool has an output schema, and the description does not hint at the return format (e.g., JSON object). For a dump tool, specifying the output structure would enhance completeness.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has no parameters, so the description does not need to add parameter meaning. Schema coverage is 100% trivially. The description is adequate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool returns the full non-expired blackboard state. The verb 'Return' and resource 'full (non-expired) blackboard state' are specific. It distinguishes from siblings like blackboard_get (single key) and blackboard_query (filtered), and from math tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

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 alternatives like blackboard_get or blackboard_query. The description only states what it does, without explicitly advising when to use it or when not to.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

blackboard_getA

Read a single belief by key. Returns None if absent or expired.

ParametersJSON Schema

Name	Required	Description	Default
`key`	Yes

Output Schema

ParametersJSON Schema

Name	Required	Description
`result`	Yes

TDQS

A3.8/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden. It discloses two failure modes (absent or expired) and the return value. For a simple read tool, this is adequate.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence that efficiently conveys purpose, behavior, and return value. No unnecessary words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's simplicity (one parameter, no nested objects, output schema exists), the description covers the key aspects: operation, parameter role, and return value. Minor gaps on key semantics are not critical.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The description does not add any detail beyond the schema regarding the `key` parameter format, constraints, or examples. With 0% schema description coverage, the description fails to compensate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool reads a single belief by key, which is a specific verb and resource. It distinguishes from siblings like `blackboard_query` (likely multiple beliefs) and `blackboard_set` (write).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage for reading a single belief but provides no explicit guidance on when to use this tool versus alternatives like `blackboard_query`. It mentions return conditions but not context for selection.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

blackboard_queryB

Query beliefs by regex pattern (over key or string value) and/or tag.

ParametersJSON Schema

Name	Required	Description	Default
`pattern`	No
`tag`	No

Output Schema

ParametersJSON Schema

Name	Required	Description
`result`	Yes

TDQS

B3.1/5.0

Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are available, so the description completely bears the burden of disclosing behavioral traits. It only states that the tool queries beliefs, implying a read operation, but does not reveal side effects, authentication needs, rate limits, or any constraints like what happens if both pattern and tag are specified. The description is minimal.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, 14-word sentence. It is extremely concise and front-loads the action ('Query beliefs'). Every word contributes to the purpose. No unnecessary information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's relative simplicity (two optional parameters) and presence of an output schema (which presumably documents return values), the description is moderately complete. However, it fails to address the logical combination of pattern and tag (AND vs OR), which is a contextual gap. The description is adequate but not thorough.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema has 0% description coverage for its two parameters. The description adds some meaning: 'pattern' is a regex applied to key or string value, and 'tag' is a tag to filter by. However, it does not fully clarify the regex format, the meaning of 'key or string value', or the logical relationship between pattern and tag (AND/OR ambiguity). It partially compensates for the missing schema descriptions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: query beliefs by regex pattern and/or tag. It specifies the resource (beliefs) and the action (query), and outlines the criteria (regex pattern on key or string value, tag). The tool is distinct from siblings like arithmetic operations and other blackboard actions, though it could explicitly differentiate from blackboard_get/dump.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives no guidance on when to use this tool versus alternatives. For example, it does not explain when to use blackboard_query instead of blackboard_get or blackboard_dump. There are no explicit context cues or exclusions provided.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

blackboard_setB

Publish a belief to the shared blackboard.

Returns the stored belief as a dict (with timestamp + provenance).

ParametersJSON Schema

Name	Required	Default
`key`	Yes
`value`	Yes
`source`	No	mcp-client
`confidence`	No
`tags`	No

Output Schema

ParametersJSON Schema

Name	Required	Description
No output parameters

TDQS

B3.1/5.0

Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries full burden for behavioral disclosure. It states that the tool returns a dict with timestamp and provenance, which is helpful. However, it does not explain side effects like overwriting existing keys, nor does it describe parameter behavior (e.g., confidence, tags) beyond the schema.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description consists of two concise sentences: the first clearly states the purpose, and the second describes the return value. There is no redundant or extraneous information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (5 parameters, no schema descriptions, no annotations), the description is incomplete. It fails to explain parameter usage or the semantics of the belief storage, which is critical for correct invocation. The mention of the return dict is a minor plus but insufficient.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters1/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has 0% description coverage, and the tool description adds no explanations for the five parameters (key, value, source, confidence, tags). An agent has no semantic understanding of what these parameters mean or how to use them beyond the schema structure.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses the specific verb 'publish' and the noun phrase 'belief to the shared blackboard', which clearly identifies the action and resource. It is easily distinguishable from sibling tools like blackboard_get (retrieve) and arithmetic tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided on when to use this tool versus alternatives such as blackboard_get or blackboard_query. The description only states what the tool does, without indicating prerequisites or appropriate contexts.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

divideA

Divide a by b. Raises if b == 0.

ParametersJSON Schema

Name	Required	Description	Default
`a`	Yes
`b`	Yes

Output Schema

ParametersJSON Schema

Name	Required	Description
`result`	Yes

TDQS

A3.6/5.0

Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description must fully disclose behavior. It only states that division raises an error if b equals zero, but omits details like return type, precision, or overflow behavior, leaving significant gaps.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is exceptionally concise with two short sentences covering the core operation and key error condition. Every word is informative with no redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the existence of an output schema (though not shown), the description is largely complete for a simple arithmetic tool. It covers the operation and main error, though it could briefly note that the result is a number.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must clarify parameter roles. The phrase 'Divide a by b' explicitly indicates that 'a' is the dividend and 'b' is the divisor, adding critical order information not evident from the schema alone.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a specific verb 'Divide' and resources 'a' and 'b', clearly defining the operation. It distinguishes from siblings like 'add', 'subtract', and 'multiply' which perform different arithmetic operations.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description only implies when to use (when division is needed) but provides no explicit context or alternatives. It does not mention when not to use or compare with related tools.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

multiplyB

Multiply two numbers.

ParametersJSON Schema

Name	Required	Description	Default
`a`	Yes
`b`	Yes

Output Schema

ParametersJSON Schema

Name	Required	Description
`result`	Yes

TDQS

B3.2/5.0

Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, and the description only says 'multiply two numbers' without disclosing any behavioral traits like overflow behavior, rounding, or error handling.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single clear sentence, concise and to the point. Could be slightly improved by including parameter details, but it is not verbose.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple arithmetic tool, the description is complete enough to understand its purpose. However, it lacks mention of return value or edge cases, but given the simplicity and presence of output schema, it is nearly adequate.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0%, so the description must add meaning. However, it only repeats 'multiply two numbers' which is already implied by the parameter names a and b, without adding any additional context about their meaning or constraints.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description 'Multiply two numbers' uses a specific verb and resource, clearly distinguishing it from sibling tools like add, divide, subtract.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use this tool vs alternatives (e.g., multiply vs add for repeated addition). The description only states what it does, not when to prefer it.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

subtractB

Subtract b from a.

ParametersJSON Schema

Name	Required	Description	Default
`a`	Yes
`b`	Yes

Output Schema

ParametersJSON Schema

Name	Required	Description
`result`	Yes

TDQS

B3.4/5.0

Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries full burden. It lacks details on number types, precision, overflow, or result handling, which are important for behavioral expectations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence with no unnecessary words. It is efficiently structured and front-loaded with the essential operation.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple arithmetic operation, the description suffices, but it could be more complete by mentioning output format or handling edge cases, especially since an output schema exists.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The description clarifies the roles of parameters a and b (a is the minuend, b is the subtrahend), but with 0% schema coverage, it does not compensate fully for the lack of parameter descriptions in the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description 'Subtract b from a' clearly specifies the verb (subtract) and the resource (two numbers), distinguishing it from sibling tools like add, multiply, and divide.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description does not provide explicit guidance on when to use this tool versus alternatives, but the purpose is implicitly understood from the tool name and statement. No exclusions or conditions are mentioned.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

A3.6/5.0

Disambiguation5/5

All tools have clearly distinct purposes: the four arithmetic operations are separate, and the four blackboard operations (set, get, query, dump) each serve unique functions. There is no overlap or ambiguity.

Naming Consistency3/5

Arithmetic tools use single verbs (add, subtract, multiply, divide) while blackboard tools use a noun_verb pattern (blackboard_dump, blackboard_get, blackboard_query, blackboard_set). This inconsistency in naming convention across the server reduces coherence.

Tool Count5/5

With 8 tools covering two distinct subdomains (arithmetic and blackboard), the count feels well-scoped. Each tool serves a clear purpose without unnecessary duplication or bloat.

Completeness4/5

The arithmetic set is complete for basic operations. The blackboard tools are mostly complete but lack a delete/remove operation, which could be a gap for typical blackboard use cases. Minor gap.

Maintenance

ActivityInactive

ResponsivenessNo issues

Resources

GitHub Repository

Need Help?

Related Servers

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

Agent Research Network
io.github.Bender1011001
Central async research commons for persistent AI agents
Knowledge & Memory Autonomous Agents Research & Data
1
OpenAkashic A
io.github.szara7678
Shared long-term memory vault for AI agents with 20 MCP tools.
Knowledge & Memory Autonomous Agents Agent Orchestration
3523
toolweave
io.github.andreysparish
One MCP endpoint for Claude, GPT & Gemini: 100+ tools + no-code connectors + agent workers.
App Automation AI & Machine Learning Agent Orchestration
2
MemoryRouter A
ai.memoryrouter
Persistent AI memory shared across Claude, ChatGPT, coding agents, and compatible MCP clients.
Knowledge & Memory Search
101

Related MCP Servers

fcop-mcp
Developer Tools File Systems Project Management
joinwell52-AI
A
license
B
quality
A
maintenance
35 MCP tools for file-based multi-agent coordination. Agents write tasks, reports, issues and reviews via structured tool calls. Works with Cursor and Claude Desktop.
Updated 8 days ago (2026-08-25 16:38 UTC)
45
2
MIT
AI Blog MCP Agent
RAG Systems Search Web Scraping
BhavinXAgheda
F
license
Not graded
quality
D
maintenance
A local AI-powered research agent that searches the web, fetches real content, and generates grounded answers using a local Ollama model, exposed as an MCP tool for Claude Desktop.
Updated 5 months ago (2026-03-20 07:48 UTC)
deep-research
Agent Orchestration Autonomous Agents
troyhantech
A
license
Not graded
quality
C
maintenance
Enables deep research tasks using a multi-agent architecture that integrates any LLM and MCP tools. Available via MCP stdio, streamable HTTP, and SSE transports.
Updated 3 months ago (2026-06-15 01:55 UTC)
17
MIT
ToolSmith Agent MCP Server
File Systems Databases
e-akgul
F
license
Not graded
quality
B
maintenance
A multi-tool task agent MCP server with file search, SQLite query, calculator, and report writing tools. Enables Claude Code, Claude Desktop, or Cursor to control the same tools used by the agent, with guardrails for safety.
Updated 2 months ago (2026-07-12 15:48 UTC)

Latest Blog Posts

Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)
By Om-Shree-0709 on July 25, 2026.
mcp
Agent Identity
OAuth 2.1
Your AI Chatbot Just Exposed Your CEO's Salary to an Intern
By Om-Shree-0709 on July 2, 2026.
Agent Identity
MCP Security
OAuth Delegation
Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)
By Om-Shree-0709 on June 30, 2026.
Agentic Ai
Prompt Injection
WebAssembly

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/SiegKat/mcp-agent-blackboard'

If you have feedback or need assistance with the MCP directory API, please join our Discord server