F
licenseD
qualityD
maintenanceProvides access to organizational Sharepoint documents through the Microsoft Graph API, enabling search and retrieval of Sharepoint content for AI assistants.
1
22
21
Entra Permissions MCP Server
by mjendza
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., "@Entra Permissions MCP Serversearch for application permissions containing 'User.Read'"
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.
Entra Permissions MCP Server
An MCP server that exposes this repo's Microsoft Entra ID / Microsoft Graph permissions data to AI agents (Claude Code, Claude Desktop, Cursor, …).
It serves the canonical permissions JSON — the same data the permissions/ React app bundles —
through MCP tools and resources.
Where the data comes from
Remote-first, local fallback. At startup the server fetches the three JSON datasets from the
public jsDelivr CDN, served from the dedicated public data store repo
mjendza/entra-id-permissions-mcp:
https://cdn.jsdelivr.net/gh/mjendza/entra-id-permissions-mcp@main/data/<file>.jsonThe data is refreshed by this repo's scrape.yaml pipeline,
which generates the JSON and pushes it to the store repo's data/ folder. Serving from the CDN
means a deployed/serverless MCP host needs no bundled data and pays no egress to host ~2 MB of
JSON — jsDelivr caches it globally. If the fetch fails (offline, CDN down, or remote disabled) the
server falls back to the local data/ files in this repo.
Prerequisite: the pipeline must have published the three
*.jsonfiles to the store repo'sdata/folder onmainat least once. Until then the server transparently uses the local fallback.
Related MCP server: Microsoft Graph MCP Server
Datasets
Source file | Records | Exposed as |
| 630 | Graph Application permissions (app roles) |
| 714 | Graph Delegated permissions (oauth2 scopes) |
| 3854 | Microsoft first-party apps + their app roles |
Tools
Tool | Purpose |
| Keyword search application permissions (Value/DisplayName/Description). |
| Keyword search delegated permissions; optional |
| Exact lookup by scope |
| Find first-party apps by display name or AppId (summary only). |
| Full record for one app (by |
| Find which Microsoft app exposes a given app role. |
Search tools return { totalMatches, returned, results } and accept an optional limit
(default 25, max 200) so large result sets stay bounded.
Resources
entra://graph/application-permissionsentra://graph/delegated-permissionsentra://microsoft-apps
Each returns the full raw dataset as application/json.
Build
cd mcp-server
npm install
npm run buildRun
stdio (local clients):
npm run start:stdio # node dist/stdio.jsStreamable HTTP (network / serverless hosting):
npm run start:http # node dist/http.js -> http://localhost:3000/mcpGET /health returns 200 {"status":"ok"}. The HTTP transport runs stateless (no session
id) which keeps serverless hosting simple; switch to session mode by supplying a
sessionIdGenerator in src/http.ts if you need server-initiated streams.
Config
ENTRA_DATA_BASE_URL— override the remote base URL (defaults to the jsDelivr CDN path above). Set to an empty string to disable remote fetching.ENTRA_DATA_LOCAL_ONLY— set to any value to skip the network entirely and read local files.ENTRA_DATA_DIR— override the local fallback directory (defaults to the repo'sdata/).PORT— HTTP port (default3000).
Register with a client
Claude Code (windows) from npm:
{
"mcpServers": {
"entra-permissions": {
"command": "cmd",
"args": ["/c", "entra-permissions-mcp"]
}
}
}Use with Claude Code (agents & commands)
The claude_code/ folder is a ready-made Claude Code workspace that
wires this MCP server together with the Microsoft Learn and Terraform MCP servers,
then layers subagents and slash commands on top so you can go from
plain-English intent to a permission table — or to ready-to-review Terraform —
without leaving the terminal.
Quick start
Launch Claude Code with claude_code/ as the working directory so it picks up
.mcp.json and .claude/:
cd claude_code
claudeApprove the MCP servers when prompted (or pre-approve them via
enabledMcpjsonServers in .claude/settings.local.json).
The MCP wiring (claude_code/.mcp.json)
Server | Transport | Purpose |
|
| This server — resolve Graph permission name → GUID + Role/Scope, look up first-party apps. |
| http | Ground |
| Docker | Terraform Registry / provider-docs tools. |
The
terraformserver needs Docker running. If you'd rather not use Docker, use theentra-sp-architect-simpleagent (below), which confirms provider syntax via themicrosoft-learnMCP instead.
Slash commands
# Resolve a capability to permission name(s) + GUID — look-up only, no files written
/ask-for-permission manage groups
# Generate Terraform for a service principal with the given Graph permissions
/create-entra-sp graph-reader User.Read.All Directory.Read.All/ask-for-permission hands off to the entra-permission-finder agent;
/create-entra-sp hands off to the entra-sp-architect agent.
Subagents
Agent | What it does | MCP tools used |
| Turns "read all users", "send mail as the user", etc. into the matching permission(s) as name + GUID + Application/Delegated. Read-only — never writes files or touches a tenant. |
|
| Resolves permission names to GUIDs, confirms |
|
| Same as above but no Docker / Terraform MCP — confirms provider syntax via |
|
Example: find a permission
/ask-for-permission manage groupsThe entra-permission-finder agent searches the entra-permissions MCP and
returns a table, least-privilege match first:
Permission (name) | GUID | Type | API | What it allows |
|
| Application (Role) | Graph | Read and write all groups |
|
| Application (Role) | Graph | Read all groups |
GUIDs above are illustrative — the agent returns the live values from the MCP and never invents a name or GUID.
Example: generate Terraform for a service principal
/create-entra-sp graph-reader User.Read.All Directory.Read.AllThe entra-sp-architect agent resolves each permission to its GUID + Role/Scope,
writes the .tf files under claude_code/terraform/, and emits one
resource_access block per permission, e.g.:
resource "azuread_application" "this" {
display_name = var.display_name
required_resource_access {
resource_app_id = "00000003-0000-0000-c000-000000000000" # Microsoft Graph
resource_access {
id = "df021288-bdef-4463-88db-98f22de89214" # User.Read.All
type = "Role"
}
resource_access {
id = "7ab1d382-f21e-4acd-a863-ba3e13f7da61" # Directory.Read.All
type = "Role"
}
}
}It then prints a name → GUID → Role/Scope resolution table and stops — you run
terraform init / plan / apply yourself. Admin consent is still required
after apply. See claude_code/README.md for full details.
Available Tools
6 toolsget_microsoft_appGet Microsoft app by AppIdA
Return the full record for a single Microsoft first-party app, including all of its exposed AppRoles, looked up by exact AppId (GUID).
ParametersJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| appId | Yes | Exact application (client) ID GUID. |
TDQS
A3.8/5.0
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It mentions the return includes AppRoles but does not disclose whether the operation is read-only, requires authentication, or has any side effects or limitations. Minimal behavioral context beyond the basic function.
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 of 20 words, front-loading the purpose and including all essential elements. No redundant or unnecessary information.
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 tool with one parameter and no output schema, the description explains the input (exact AppId) and output (full record with AppRoles). It could mention the output format (e.g., JSON) but is nearly complete given the tool's simplicity.
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 only parameter, appId, is fully described in the schema (100% coverage). The description reinforces that it is an exact GUID lookup but adds little additional meaning beyond the schema's own description. Per guidelines, baseline 3 is appropriate.
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 verb 'Return' and the resource 'full record for a single Microsoft first-party app', including the differentiator 'including all of its exposed AppRoles' and the lookup method 'by exact AppId (GUID)'. It distinguishes from sibling tools like search_microsoft_apps by specifying an exact ID lookup.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage when you have an exact AppId and need the full record, but does not explicitly state when not to use or mention alternative tools. Context with siblings like search_microsoft_apps suggests this is for single-record retrieval, but explicit when-not guidance is absent.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
get_permissionGet permission by scope value or GUIDA
Exact lookup of a Graph permission by its scope Value (e.g. 'User.Read.All') or its GUID Id. Searches Application and/or Delegated datasets. A scope can exist in both, so matches from each dataset are returned. Provide either value or id.
ParametersJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| id | No | Exact permission GUID. | |
| kind | No | Which dataset(s) to search. Default: any. | |
| value | No | Exact scope value, e.g. "User.Read.All". |
TDQS
A4/5.0
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full burden. It discloses that searches cover Application and/or Delegated datasets and that a scope can exist in both, returning matches from each. However, it does not clarify behavior if both value and id are provided or if neither is provided, leaving some ambiguity. No annotation contradiction.
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 concise at three sentences, front-loads the core action, and contains no unnecessary words. Every sentence adds value.
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 tool with 3 parameters, no annotations, and no output schema, the description covers most key aspects: purpose, parameter usage, and dual dataset behavior. It is missing details on output format and handling of edge cases like providing both or neither parameter, but overall it is fairly complete.
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 coverage is 100%, establishing a baseline of 3. The description adds meaning by explaining the dual dataset behavior and the purpose of the 'kind' parameter, which goes beyond the schema's description. It also reinforces the 'either value or id' requirement.
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 does an exact lookup of a Graph permission by scope value or GUID. It distinguishes from sibling search tools by emphasizing 'exact lookup' and specifying the use of either value or id.
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 when to use the tool (for exact lookup when the value or GUID is known) but does not explicitly mention when not to use it or contrast it with sibling search tools. Some guidance is provided by stating 'Provide either value or id', but more direct comparison would improve clarity.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
search_app_rolesSearch app roles across Microsoft appsA
Search the app roles exposed by all Microsoft first-party apps by keyword (role Value, DisplayName, or Description). Each result includes the owning app's AppId and AppDisplayName — useful to find which app exposes a given role.
ParametersJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Max results to return (default 25). | |
| query | Yes | Role keyword, e.g. "EventGrid" or "Policy.Read". |
TDQS
A4.2/5.0
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full burden. It discloses the search scope (keyword in Value, DisplayName, Description) and output elements (AppId, AppDisplayName). It does not mention auth, rate limits, or edge cases, but for a search tool this is adequate 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?
Two sentences, front-loaded with action and scope. Every word adds value. No fluff.
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 2 params and no output schema, the description explains output content (AppId, AppDisplayName) which is helpful. It covers essential context for a search tool but lacks details on error handling, pagination beyond limit, or no-result scenarios.
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?
Schema coverage is 100%, so baseline is 3. The description's example for query ('EventGrid', 'Policy.Read') adds marginal value beyond the schema description. The limit parameter is not elaborated in the description, so no additional meaning beyond 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 clearly states it searches app roles by keyword across Microsoft first-party apps. It specifies the fields searched (Value, DisplayName, Description) and notes the output includes owning app's AppId and AppDisplayName. This distinguishes it from sibling tools like search_graph_application_permissions or search_microsoft_apps.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies when to use: to find which app exposes a given role. However, it does not explicitly state when not to use this tool or compare it with alternatives like search_graph_application_permissions. It provides clear context but lacks exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
search_graph_application_permissionsSearch Graph application permissionsA
Search Microsoft Graph Application permissions (app roles) by keyword across the scope Value, DisplayName, and Description. Application permissions grant app-only (no signed-in user) access.
ParametersJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Max results to return (default 25). | |
| query | Yes | Keyword, e.g. "AccessReview" or "User.Read". |
TDQS
A3.9/5.0
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, description carries full burden. It discloses search scope and permission type, but omits details on pagination, rate limits, or behavior for broad queries. Partial transparency but not comprehensive.
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?
Two concise sentences: first defines action and scope, second clarifies permission type. No wasted words; front-loaded with key info.
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 no output schema, description lacks return format details. Missing ordering or match type information. Adequate but not fully complete for a search tool.
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 already describes both parameters (query, limit) clearly. Description adds value by specifying the search scope (Value, DisplayName, Description), which provides context beyond the schema's 'keyword' description.
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?
Description clearly states the tool searches Graph application permissions by keyword across Value, DisplayName, and Description. It specifies 'application permissions grant app-only access,' distinguishing it from delegated permissions tools like search_graph_delegated_permissions.
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?
No explicit guidance on when to use this tool vs alternatives like search_app_roles or search_microsoft_apps. It implies searching for application permissions but lacks exclusion criteria or context for when delegated permissions are more appropriate.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
search_graph_delegated_permissionsSearch Graph delegated permissionsA
Search Microsoft Graph Delegated permissions (oauth2 scopes) by keyword across the scope Value and the admin/user consent display names and descriptions. Optionally filter by consent Type (Admin or User).
ParametersJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| type | No | Filter by consent type: Admin (admin consent required) or User. | |
| limit | No | Max results to return (default 25). | |
| query | Yes | Keyword, e.g. "Mail.Read" or "calendar". |
TDQS
A3.8/5.0
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It discloses the search fields and filter option, but fails to mention if the operation is read-only, rate limits, or pagination behavior. For a search operation, these are 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?
Two sentences, no wasted words. Front-loaded with the action and resource. Efficient and clear.
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 is simple with 3 parameters and no output schema, the description adequately covers purpose and parameters. It could be more complete by noting that results are limited by the 'limit' parameter and that the operation is read-only, but overall it's sufficient.
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 coverage is 100%, baseline 3. The description adds value by explaining that 'query' searches across scope value, display names, and descriptions, which is more specific than the schema description. It also reinforces the 'type' filter meaning. No new info for 'limit' though.
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 searches 'Microsoft Graph Delegated permissions' by keyword across scope values, display names, and descriptions. The verb 'Search' and resource are specific. The sibling 'search_graph_application_permissions' implies this is for delegated permissions, distinguishing it.
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 explains the search scope and optional filtering by consent type. However, it does not explicitly state when to use this tool versus siblings like 'search_graph_application_permissions' or 'search_app_roles'. Usage context is implied but not explicit.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
search_microsoft_appsSearch Microsoft first-party appsA
Search Microsoft first-party applications by display name or AppId. Returns a summary (without the full AppRoles array); use get_microsoft_app for an app's roles.
ParametersJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Max results to return (default 25). | |
| query | Yes | App display name or AppId, e.g. "Microsoft Graph". |
TDQS
A4/5.0
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description must handle transparency. It discloses that the result is a summary without AppRoles, but does not mention idempotency, auth requirements, or potential mutation. For a search tool, this is adequate but not thorough.
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 two concise sentences with no fluff. It front-loads the core purpose and provides a key distinction, making every sentence valuable.
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?
The description covers the return format (summary without roles), default limit (25), and the relationship with get_microsoft_app. For a simple search tool with no output schema, this is fairly complete, though it lacks pagination details.
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?
Schema coverage is 100%, with both parameters having descriptions in the schema. The description adds no extra meaning beyond what the schema provides, so baseline score of 3 is appropriate.
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 action is to search Microsoft first-party applications by display name or AppId, and it distinguishes itself from get_microsoft_app by noting it returns a summary without AppRoles array.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explicitly tells the agent to use get_microsoft_app for an app's roles, providing a clear alternative. However, it does not address when to use other sibling tools like search_app_roles or search_graph_permissions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
TDQS
A4.2/5.0
Disambiguation5/5
Each tool has a distinct and well-defined purpose: retrieving an app's full record, looking up a specific permission, searching app roles, searching application permissions, searching delegated permissions, and searching Microsoft apps. There is no functional overlap, and the descriptions clearly differentiate them.
Naming Consistency5/5
All tools follow a consistent verb_noun pattern using snake_case: get_microsoft_app, get_permission, search_app_roles, search_graph_application_permissions, search_graph_delegated_permissions, search_microsoft_apps. Naming is predictable and uniform.
Tool Count5/5
With 6 tools, the server is well-scoped for its purpose of exploring Microsoft Entra permissions and apps. The count is neither too few nor too many, and each tool serves a clear role without redundancy.
Completeness5/5
The tool surface covers all major read operations for the domain: searching and retrieving both apps and permissions (application and delegated). There are no obvious gaps, as the server appears designed for read-only exploration, and the tools handle the core workflows.
Maintenance
ActivityActive
ResponsivenessSyncing
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Connectors
Permissioned access to Outlook, OneDrive and Teams via the user's own Microsoft account
Official Microsoft MCP Server to query Microsoft Entra data using natural language
Runtime permission, approval, and audit layer for AI agent tool execution.
Your company's brain for AI agents. Cited, permission-aware knowledge across every system.
Related MCP Servers
- AlicenseNot gradedqualityFmaintenanceEnables AI assistants to interact with Microsoft 365 services (users, mail, calendar, files) via Microsoft Graph API.461MIT
Glean Remote MCP Serverofficial
AlicenseNot gradedqualityCmaintenanceEnables AI assistants and developer tools to securely access and interact with an organization's enterprise knowledge, documents, and people through natural language while respecting existing access permissions.164MIT- AlicenseNot gradedqualityDmaintenanceEnables AI assistants to interact with Microsoft 365 through the Microsoft Graph API, including searching Teams messages, managing chats, and sending messages.77MIT
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
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/mjendza/entra-id-permissions-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server