Provides tools for searching, reading, creating, and appending Notion pages, as well as managing project context, logging decisions, and generating prompts from Notion data.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Notion MCP search for launch checklist"
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.
A secure, open-source Model Context Protocol server for connecting AI agents and apps to Notion.
We built this because the existing hosted/default Notion MCP flow was down or unreliable when we needed it. Instead of waiting on a black-box integration, this project gives teams a simple Notion bridge they can own, run locally, deploy privately, customize, and audit.
Notion MCP is designed to work with any app or team setup:
No agent architecture yet: use it as a clean local Notion MCP server for search, read, create, and append workflows.
Intermediate agent setup: connect it to Codex, Claude Desktop, Cursor, or your own assistant as a safe documentation bridge.
Advanced multi-agent architecture: use it as the Notion knowledge layer behind a lead agent, task agents, product agents, release agents, or app-specific orchestration.
The goal is easy, useful, accommodating infrastructure: Notion stays your source of truth, and agents only get the tools you intentionally expose.
V1 includes:
Search Notion pages.
Retrieve Notion page metadata, blocks, and readable plain text.
Create new Notion pages under a configured root page.
Append content to existing Notion pages.
List configured apps/projects.
Retrieve lightweight app/project context.
Log decisions to Notion.
Generate simple Codex-ready prompts from project context.
Audit-log every tool call.
Enforce risk levels for every tool.
V1 intentionally does not include destructive tools, production-control tools, billing actions, auth changes, email sending, deployments, or unrestricted app control.
Related MCP server: Notion MCP Server
AI Client or Agent
|
| calls approved MCP tools
v
Notion MCP
|
| uses a scoped Notion integration token
v
Notion Workspace or Page TreeFor more advanced teams, you can add app connectors behind the same permission model:
Lead Agent
|
v
Notion MCP / App Gateway
|
|-------------------------------
| | | |
Notion App API CI Tool Support ToolThe important rule: agents should call approved MCP tools, not receive unrestricted direct access to every system.
npm install
npm run build
cp .env.example .envCreate a Notion integration at:
https://www.notion.com/my-integrations
Then:
Copy the integration secret into NOTION_TOKEN.
Open the Notion page you want this server to access.
Use Notion's page menu to connect/share the page with your integration.
Copy the page ID into NOTION_ROOT_PAGE_ID.
.env:
NOTION_TOKEN=
NOTION_ROOT_PAGE_ID=
SUPABASE_URL=
SUPABASE_SERVICE_ROLE_KEY=
MCP_GATEWAY_API_KEY=
OPENAI_API_KEY=
NODE_ENV=development
AUDIT_LOG_FILE=.audit/tool-calls.jsonlOnly NOTION_TOKEN and NOTION_ROOT_PAGE_ID are required for the core Notion tools. Supabase is optional.
Development:
npm run devBuilt server:
npm run build
npm startStdio wrapper for MCP clients:
./scripts/run-mcp.shThe wrapper loads .env from the repo so you do not need to copy secrets into global client config files.
./scripts/register-codex-mcp.sh notion_mcp
codex mcp listRestart Codex or open a fresh session after registration.
Equivalent config:
[mcp_servers.notion_mcp]
command = "/absolute/path/to/notion-mcp/scripts/run-mcp.sh"
args = []
cwd = "/absolute/path/to/notion-mcp"
startup_timeout_sec = 120Generic MCP client config:
{
"mcpServers": {
"notion-mcp": {
"command": "/absolute/path/to/notion-mcp/scripts/run-mcp.sh",
"args": []
}
}
}This works best for desktop/local agent clients. Hosted deployments can be added later with HTTP transport, auth, and tenancy controls.
notion_searchSearch the connected Notion workspace/page tree.
{ "query": "launch checklist" }Returns:
{
"results": [
{
"title": "Launch Checklist",
"pageId": "notion-page-id",
"type": "page",
"url": "https://notion.so/...",
"lastEditedTime": "timestamp",
"summary": "Notion page titled \"Launch Checklist\"."
}
]
}notion_get_pageRetrieve a Notion page and block content.
{ "pageId": "notion-page-id" }Returns pageId, title, url, raw blocks, and extracted plainText.
notion_create_pageCreate a new page under NOTION_ROOT_PAGE_ID or a provided parent page.
{
"title": "New Project Decision",
"content": "Content to add to the page",
"parentPageId": "optional-page-id"
}Create-only. It does not overwrite existing pages.
notion_append_to_pageAppend content to an existing page.
{
"pageId": "notion-page-id",
"content": "New decision or note to append"
}Append-only. It does not delete or replace page content.
project_list_appsReturns project/app names configured in src/tools/projectTools.ts.
project_get_context{ "projectName": "Example App" }Use this to give agents a lightweight local context map before they search deeper in Notion.
mission_log_decision{
"projectName": "Example App",
"decisionTitle": "Use MCP as the documentation bridge",
"decisionDetails": "Agents can write safe append-only documentation through MCP.",
"category": "architecture"
}codex_generate_prompt{
"projectName": "Example App",
"goal": "Implement the next safe documentation workflow",
"constraints": ["Use existing app architecture", "Prioritize safe implementation"]
}Every tool has a risk level.
Executable in V1:
read: search, retrieve, list context.
safe_write: create or append documentation without deleting or replacing content.
Prepared but blocked in V1:
operational: non-destructive live app operations.
restricted: destructive, sensitive, financial, production, auth, access, or security-changing actions.
Human approval should be required before any future tool can:
Delete content.
Change user access.
Change billing or license state.
Lock users out.
Send external emails.
Modify production settings.
Trigger production deployments.
Change security policies.
Change secrets, API keys, or auth settings.
Recommended security practices:
Use a dedicated Notion integration token for each deployment.
Share only the specific Notion pages/databases the server needs.
Keep .env out of git.
Rotate tokens if they are exposed.
Prefer local/file audit logs for prototypes and Supabase/Postgres audit logs for teams.
Add new tools behind explicit schemas, risk levels, and tests.
Every tool call is logged with:
id
timestamp
toolName
riskLevel
inputSummary
success
errorMessage
requestingAgent
projectName
notionPageId
durationMs
If Supabase is configured, logs are inserted into tool_calls. Otherwise logs are written to .audit/tool-calls.jsonl.
Optional Supabase table:
create table if not exists tool_calls (
id uuid primary key,
timestamp timestamptz not null,
tool_name text not null,
risk_level text not null,
input_summary text not null,
success boolean not null,
error_message text,
requesting_agent text,
project_name text,
notion_page_id text,
duration_ms integer not null
);No app architecture:
Use Notion MCP as your first bridge between AI and project docs.
Keep decisions, prompts, checklists, notes, and roadmaps in Notion.
Intermediate app architecture:
Configure your projects in src/tools/projectTools.ts.
Use mission_log_decision and codex_generate_prompt to keep implementation work tied to Notion context.
Advanced agent architecture:
Add connector folders under src/connectors/.
Keep app-specific APIs behind approved tools.
Require human approval for operational and restricted actions.
Use audit logs to review what each agent did.
Edit:
src/tools/projectTools.tsto define your own apps/projects.
Add future connectors under:
src/connectors/When adding a new tool:
Define a Zod input schema.
Assign a risk level.
Wrap execution with runLoggedTool.
Keep restricted actions blocked unless you add an explicit human approval workflow.
Add focused tests.
npm test
npm run typecheck
npm run buildManual tests:
Run notion_search with a known query.
Run notion_get_page with a valid page ID.
Run notion_create_page without parentPageId and confirm it appears under NOTION_ROOT_PAGE_ID.
Run notion_append_to_page and confirm existing page content is preserved.
Remove Supabase env vars and confirm .audit/tool-calls.jsonl receives entries.
Remove NOTION_TOKEN and confirm Notion tools fail with a clear missing environment error.
Use an invalid Notion page ID and confirm the tool fails and logs the failure.
Confirm operational/restricted risk levels throw in tests.
V1 is a local stdio MCP server. That is the simplest and safest first shape for personal agents, desktop clients, and local developer workflows.
For hosted use, add:
HTTP or Streamable HTTP transport.
API key or OAuth auth.
Per-tenant Notion tokens.
Rate limiting.
Centralized audit logging.
Deployment-specific secret management.
Do not deploy a public shared instance with one global Notion token. Each user/team should bring their own Notion integration and credentials.
MIT
Generate a Codex-ready implementation prompt from configured project context and a current goal. Risk: read.
| Name | Required | Description | Default |
|---|---|---|---|
| goal | Yes | ||
| constraints | No | ||
| projectName | Yes | ||
| requestingAgent | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description adds 'Risk: read', confirming it is a read-only operation. Annotations already set readOnlyHint=true, so there is no contradiction. However, the description does not disclose any additional behavioral traits beyond what annotations provide.
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 concise with two short sentences, but the brevity sacrifices informative content. It is front-loaded with the key action but lacks necessary details.
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?
Given the tool has 4 parameters, no output schema, and read-only annotations, the description is not complete. It does not explain return values, parameter details, or usage context, leaving significant gaps for an AI agent.
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?
With 0% schema description coverage, the description should compensate but only mentions 'from configured project context and a current goal'. It does not explain the purpose of 'constraints', 'requestingAgent', or how 'goal' and 'projectName' relate. This is insufficient for an agent to understand parameter semantics.
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 clearly states the tool generates a 'Codex-ready implementation prompt' from 'configured project context and a current goal'. The verb 'generate' and resource 'implementation prompt' are specific, and it distinguishes from sibling tools like notion_* or project_get_context. However, 'configured project context' is somewhat vague.
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?
The description provides no guidance on when to use this tool vs siblings, no conditions, prerequisites, or alternatives. It only states what the tool does, not when it is appropriate to invoke.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Log an architecture, product, business, security, or implementation decision to Notion. Risk: safe_write.
| Name | Required | Description | Default |
|---|---|---|---|
| category | No | implementation | |
| projectName | Yes | ||
| decisionTitle | Yes | ||
| decisionDetails | Yes | ||
| requestingAgent | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations indicate non-destructive write (readOnlyHint=false, destructiveHint=false). The description adds 'Risk: safe_write', clarifying the write is safe but doesn't elaborate on side effects, like which Notion page is updated or whether existing content is modified. Adds some context beyond annotations but could be more thorough.
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 extremely concise: two sentences, no filler, front-loaded with purpose. Every word adds value.
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 tool with 5 parameters, 3 required, no output schema, and no parameter descriptions, the description is too sparse. It does not explain the return value, which Notion page the decision is logged to, or how the parameters should be used. This lacks completeness for an agent to use it reliably.
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?
With 0% schema description coverage, the description must explain parameters, but it only covers the 'category' parameter implicitly via listing categories. It does not describe 'projectName', 'decisionTitle', 'decisionDetails', or 'requestingAgent', leaving their semantics unclear. This is a significant gap.
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 clearly states the verb 'log' and the resource 'decision to Notion', listing specific categories (architecture, product, business, security, implementation). This distinguishes it from sibling tools like notion_create_page or codex_generate_prompt, which have different purposes.
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?
The description implies usage when a decision needs to be recorded, but it does not explicitly state when not to use this tool or provide alternatives. Given siblings include other Notion tools (append, create, get, search), the lack of exclusion criteria limits guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Append content to an existing Notion page without replacing or deleting content. Risk: safe_write.
| Name | Required | Description | Default |
|---|---|---|---|
| pageId | Yes | ||
| content | Yes | ||
| requestingAgent | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description adds value beyond annotations by explicitly stating 'without replacing or deleting content' and noting 'Risk: safe_write'. This provides context that complements the destructiveHint=false annotation. It does not disclose behavior on missing page IDs or rate limits, but the key behavioral traits are covered.
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 extremely concise: one sentence plus a two-word phrase. Every word serves a purpose, and key information is front-loaded. No unnecessary content.
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 simple append tool with no output schema, the description provides the essential action and safety hint. However, it lacks information about error handling, prerequisites (e.g., page existence), or return values, leaving some gaps for complete agent understanding.
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?
Schema description coverage is 0%, but the description only mentions 'content' generically and does not explain the purpose or format of pageId, content, or requestingAgent. No additional parameter semantics are provided, failing to compensate for the lack of schema descriptions.
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 clearly states the verb 'Append' and the resource 'content to an existing Notion page', distinguishing it from sibling tools like notion_create_page and notion_get_page. It explicitly notes that content is added without replacing or deleting, which clarifies its unique function.
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?
The description implies usage for appending content to an existing page, and mentions 'safe_write' as a risk indicator. However, it does not explicitly state when not to use it or compare to alternatives like notion_create_page, leaving some ambiguity for the agent.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Create a new Notion page under the configured root page or provided parent page. Risk: safe_write.
| Name | Required | Description | Default |
|---|---|---|---|
| title | Yes | ||
| content | Yes | ||
| parentPageId | No | ||
| requestingAgent | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already indicate non-read-only and non-destructive behavior. The description adds 'Risk: safe_write', clarifying that it is a write operation but safe (no unintended damage). This extra context slightly raises transparency, though more details (e.g., permission requirements) could be added.
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 extremely concise: two sentences, no wasted words. Every sentence adds value (purpose and safety hint). It is front-loaded with the action and location, making it easy to scan.
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?
Given the tool has 4 parameters with no schema descriptions, no output schema, and no explanation of content format (e.g., Markdown), the description is too brief. It lacks details on default behavior (e.g., root page if parentPageId omitted), return values, and prerequisites, making it incomplete for effective invocation.
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?
Schema description coverage is 0% (no parameter descriptions). The description mentions 'parent page' which relates to the optional 'parentPageId', but provides no further meaning for parameters like 'title', 'content', or 'requestingAgent'. It fails to compensate for missing schema descriptions, leaving agents to guess formats or constraints.
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 clearly states the verb 'create' and the resource 'Notion page', and specifies the location context ('under the configured root page or provided parent page'). This distinguishes it from sibling tools like 'notion_append_to_page' (which appends to an existing page) and 'notion_get_page' (which retrieves).
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?
The description implies use for creating new pages, but provides no explicit guidance on when to use this tool versus alternatives (e.g., 'notion_append_to_page' for adding content to an existing page). No when-not or alternative scenarios are mentioned, leaving the agent to infer from context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Retrieve a Notion page and its block content. Risk: read.
| Name | Required | Description | Default |
|---|---|---|---|
| pageId | Yes | ||
| requestingAgent | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false. The description adds 'Risk: read' which is consistent but adds minimal value. No additional behavioral context (e.g., rate limits, auth needs, output format) is provided beyond what annotations convey.
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 a single, concise sentence that efficiently communicates the core purpose. However, it could be enhanced with additional context without becoming verbose, such as mentioning the return format or common use cases.
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?
Given the tool is a simple get operation with good annotations, the description provides the essential action and risk. However, it lacks information about the return value (since no output schema exists), potential errors, and how to handle the 'pageId' format. The description is adequate but not fully complete for an agent to use without additional context.
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?
Schema description coverage is 0%, meaning the input schema provides no descriptions for parameters. The description mentions retrieving a page and its block content, which gives context for the pageId parameter, but the requestingAgent parameter is completely undocumented. The description fails to compensate for the lack of schema descriptions.
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 clearly states the verb 'retrieve' and the resource 'Notion page and its block content', providing a specific and unambiguous purpose. It distinguishes from sibling tools like notion_append_to_page (write) and notion_create_page (write), and notion_search (search-based retrieval).
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?
The description lacks any guidance on when to use this tool versus alternatives such as notion_search. No context is provided about prerequisites, required permissions, or exclusions, leaving the agent to infer usage from the tool name alone.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search the connected Notion workspace for pages matching a query. Risk: read.
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | ||
| requestingAgent | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint, and destructiveHint false, covering safety. The description adds 'Risk: read' which is redundant. It does not disclose additional behavioral traits like whether it searches page titles only or full text, or if there is pagination or result limits.
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 (one sentence plus a note), which is concise. However, the 'Risk: read' note is unnecessary given annotations. Every word earns its place, but could be more informative without increasing length significantly.
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?
Given a search tool with no output schema and minimal parameter descriptions, the description is insufficient for an agent to understand return behavior, search scope, or limitations. It lacks details on results structure, pagination, or query capabilities.
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?
With 0% schema description coverage, the description adds minimal semantic value. It mentions 'matching a query' for the query parameter but does not explain its syntax, supported features, or the purpose of 'requestingAgent'. The schema provides constraints but no semantics.
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 clearly states it searches the connected Notion workspace for pages matching a query, which is a specific verb-resource combination that distinguishes it from sibling tools like notion_get_page (retrieve specific page) or notion_create_page (create new page).
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?
The description does not provide explicit guidance on when to use or not use this tool versus alternatives. It only states 'Risk: read', which implies safe use, but lacks context such as 'Use this to find pages by keyword; use notion_get_page to retrieve full page content once found.'
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Retrieve configured project context. Risk: read.
| Name | Required | Description | Default |
|---|---|---|---|
| projectName | Yes | ||
| requestingAgent | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint, and destructiveHint. The description adds only 'Risk: read', which is redundant. No additional behavioral traits (e.g., performance, data scope) are disclosed beyond the annotations.
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 extremely short (one sentence), which is concise but at the cost of missing critical details. It is front-loaded but under-specifies the tool's behavior and parameters.
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?
Given the low schema coverage and absence of an output schema, the description fails to explain what the tool returns or what constitutes 'configured project context'. The 'requestingAgent' role is unclear, leaving the agent ill-equipped 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?
Schema description coverage is 0%, meaning neither the schema nor the description provides any explanation for the two parameters ('projectName', 'requestingAgent'). The agent receives no semantic hints about how to use these 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 clearly states a specific action ('Retrieve') and resource ('configured project context'), with 'Risk: read' indicating a safe read operation. This distinguishes it from sibling tools like 'notion_get_page' or 'project_list_apps'.
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 is provided on when to use this tool versus its siblings. The description lacks context on prerequisites, scenarios, or when not to use it, leaving the agent without decision support.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Return app/project names configured for this workspace. Risk: read.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already provide readOnlyHint, idempotentHint, destructiveHint. The description adds 'Risk: read', which is consistent but adds little value beyond annotations.
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?
Extremely concise: one clear sentence plus a brief risk note. Every phrase earns its place with no redundancy.
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?
With no output schema and simple purpose, the description adequately conveys the tool's function. Could be slightly improved by specifying output format (e.g., array of strings), but realistically sufficient for a list operation.
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?
Tool has zero parameters, so baseline is 4. Description adds no parameter info, but none is needed since schema coverage is 100% and no parameters exist.
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 clearly states the tool returns app/project names for the workspace, using specific verb 'Return' and resource 'app/project names'. It distinguishes from sibling tools like project_get_context or notion_search which have different purposes.
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 explicit guidance on when to use this tool versus alternatives. The description only implies its usage for listing app/project names, but does not provide when-not-to-use or mention sibling tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Each tool has a clearly distinct purpose: codex prompt generation, decision logging, Notion page operations (append, create, get, search), and project context retrieval. No overlaps.
Names follow snake_case and use a <domain>_<action> pattern, but prefixes vary (codex_, mission_log_, notion_, project_). Within each domain, naming is consistent; overall pattern is readable but not fully uniform.
8 tools is well-scoped for a Notion integration covering core operations (create, get, search, append) plus additional project context and decision logging. No redundancy.
Covers create, read, search, and append for Notion pages, but missing update and delete operations. Project context and decision logging are included, but the Notion surface is incomplete for full CRUD.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
MCP server connecting AI agents to 100+ apps (Gmail, Slack, Notion, GitHub) via one-click OAuth.
The Box MCP server is a secure gateway that connects external AI agents to enterprise content stored in Box, enabling agent-based document access, advanced search, and multi-file analysis while preserving Box security policies. It provides capabilities including keyword search, Box AI-powered Q&A across files, metadata extraction, file management, and authentication, all validated against Box's granular permission controls. The server integrates with major AI platforms like Anthropic Claude, Microsoft Copilot Studio, and Mistral Le Chat, and is available both as a Box-hosted remote server and a self-hosted open-source Python project.
A comprehensive Model Context Protocol (MCP) server that enables AI assistants to interact with yo…
Shared, permission-aware company context for AI agents, with provenance, approvals and audit.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/Limelight-Management-Group/notion-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
