SkillAgentSearch skills...

mcp

A collection of Model Context Protocol (MCP) servers, clients and developer tools by IBM.

Install / Use

claude mcp add IBM -- npx -y github:IBM/mcp

If the server publishes to npm under a different name, use that package instead — check the repo README.

About this skill
🔌

MCP Server

Model Context Protocol server

Quality Score

43/100

Supported Platforms

Claude Code
Claude Desktop

Our assessment of mcp

mcp scores 43/100 on our quality scale, 4331st of 4,614 Development & Engineering skills we index.

Its MCP Server is 4.9 KB long, written without headings and no code examples: a solid amount of guidance for an agent.

It has no GitHub stars yet, so there is no community track record; judge it on its content.

Substance
26/30
Structure
0/20
Description
12/15
Adoption
0/20
Freshness
5/15

Maintenance, license and trust

  • We could not determine when the repository was last updated.
  • Our last check on 2026-09-25 found the source still online.
  • No license is declared. By default that means all rights are reserved: you can read it, but reusing or redistributing it is not clearly permitted. Ask the author before building on it commercially.
  • Its trust signals score 68/100, with 3 cautions from licensing, adoption, age or documentation. These come from repository metadata, not a code audit — read the skill file before letting an agent act on it.

Safety scan

Review

Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review judged it risky: The `carbon-mcp` server includes `"alwaysAllow": ["docs_search", "code_search"]`, which disables permission prompts for those tools and weakens the agent's safeguards.

AI review: risky

  • The `carbon-mcp` server includes `"alwaysAllow": ["docs_search", "code_search"]`, which disables permission prompts for those tools and weakens the agent's safeguards.
  • The file instructs the agent to launch many third-party MCP servers (via `uvx`, `npx`, `docker`, HTTP) and supply credentials/tokens, so misconfiguration or compromise of any server could expose sensitive data.
  • Several servers are installed directly from Git repositories (e.g., `uvx --from git+https://github.com/...`), which runs code from a remote source rather than a published package.

AI review by kimi-k2.7-code on 2026-09-23. Automated pattern scan on 2026-09-24. It catches known dangerous patterns, not every risk — read a skill before letting an agent act on it.

mcp compared with similar skills

All 4 of these similar skills score higher than mcp; compare them before choosing.

SkillScoreStarsUpdatedFormat
mcp (this skill)by IBM430—MCP Server
taste-skillby Leonxlnx100111.0k1d agoCLAUDE.md
Agent-Reachby Panniantong100109.5k1d agoCLAUDE.md
headroomby headroomlabs-ai10079.0ktodayCLAUDE.md
ai-job-searchby ai-job-search-dev10070.0ktodayCLAUDE.md

Frequently asked questions

How do I install mcp?
Run claude mcp add IBM -- npx -y github:IBM/mcp. The install tabs above show the steps for each supported agent.
Which AI agents does mcp work with?
It is written for Claude Code and Claude Desktop, as a MCP Server file. Other agents that read the same format can often use it too.
Is mcp safe to use?
Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review judged it risky: The carbon-mcp server includes "alwaysAllow": ["docs_search", "code_search"], which disables permission prompts for those tools and weakens the agent's safeguards. It declares no license and scores 68/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
Is mcp still maintained?
We could not determine when the repository was last updated.

{ "mcpServers": { "core-cs-mcp-server": { "command": "uvx", "args": [ "--from", "git+https://github.com/ibm-ecm/ibm-content-services-mcp-server", "core-cs-mcp-server" ], "env": { "USERNAME": "YOUR_USERNAME", "PASSWORD": "YOUR_PASSWORD", "SERVER_URL": "YOUR_GRAPHQL_SERVER_ENDPOINT", "OBJECT_STORE": "YOUR_OBJECT_STORE_NAME" } }, "carbon-mcp": { "type": "streamable-http", "url": "https://mcp.carbondesignsystem.com/mcp", "disabled": false, "timeout": 600, "headers": { "Authorization": "Bearer <TOKEN>", "X-MCP-Session": "<opaque-session-id>" }, "alwaysAllow": ["docs_search", "code_search"] }, "ibm-decision-intelligence-mcp-server": { "command": "npx", "args": ["-y", "di-mcp-server"], "env": { "APIKEY": "<APIKEY>", "URL": "https://<TENANT_NAME>.decision-prod-us-south.decision.saas.ibm.com/ads/runtime/api/v1" } }, "ibm-mq-mcp-server": {}, "ibm-odm-decision-mcp-server": { "command": "uvx", "args": [ "--from", "git+https://github.com/DecisionsDev/ibm-odm-decision-mcp-server", "start" ] }, "ibm-baw-mcp-server": { "command": "uvx", "args": [ "--from", "git+https://github.com/ibmbpm/ibm-baw-mcp-server", "ibm-baw-mcp-server" ], "env": { "ENDPOINT": "YOUR_WORKFLOW_ENDPOINT", "USERID": "YOUR_WORKFLOW_USERNAME", "PASSWORD": "YOUR_WORKFLOW_PASWORD" } }, "astra-db-mcp-server": { "command": "npx", "args": ["-y", "@datastax/astra-db-mcp"], "env": { "ASTRA_DB_APPLICATION_TOKEN": "YOUR_ASTRA_DB_TOKEN", "ASTRA_DB_API_ENDPOINT": "YOUR_ASTRA_DB_ENDPOINT" } }, "docling-mcp-server": { "command": "uvx", "args": ["--from=docling-mcp", "docling-mcp-server"] }, "ibm_watsonxdata_local_mcp_server": { "type": "stdio", "command": "uvx", "args": ["ibm-watsonxdata-dl-retrieval-mcp-server", "--transport", "stdio"], "env": { "WATSONX_DATA_API_KEY": "YOUR_API_KEY", "WATSONX_DATA_RETRIEVAL_ENDPOINT": "YOUR_RETRIVAL_ENDPOINT", "WATSONX_DATA_TOKEN_GENERATION_ENDPOINT": "YOUR_BEARER_TOKEN_ENDPOINT", "DOCUMENT_LIBRARY_API_ENDPOINT": "YOUR_DOCUMENT_LIBRARY_ENDPOINT", "LH_CONTEXT": "SAAS" } }, "ibm_watsonxdata_remote_mcp_server": { "url": "https://YOUR_INSTANCE_URL/api/v1/mcp/", "headers": { "authorization": "Bearer TOKEN" }, "type": "http" }, "ibmcloud-mcp-server": {}, "tim-mcp-server": { "command": "uvx", "args": [ "--from", "git+https://github.com/terraform-ibm-modules/tim-mcp.git", "tim-mcp" ], "env": { "GITHUB_TOKEN": "<your_github_token>" } }, "ibmcloud-code-engine-mcp-server": {}, "ibmcloud-vpc-mcp-server": {}, "ibmi-mcp-server": { "command": "npx", "args": ["-y", "@ibm/ibmi-mcp-server@latest"], "env": { "TOOLS_YAML_PATH": "/path/to/your/tools.yaml", "DB2i_HOST": "your-ibmi-host.com", "DB2i_USER": "your-username", "DB2i_PASS": "your-password", "DB2i_PORT": "8076" } }, "terraform-mcp-server": { "command": "docker", "args": [ "run", "-i", "--rm", "-e", "TFE_ADDRESS=<HCP Terraform or TFE Address>", "-e", "TFE_TOKEN=<HCP Terraform or TFE Token>", "hashicorp/terraform-mcp-server" ] }, "ibm-instana-mcp-server": {}, "ibm-storage-insights-mcp-server": {}, "consul-mcp-server": { "command": "docker", "args": [ "run", "--rm", "-i", "-e", "CONSUL_HTTP_ADDR=<Consul HTTP Address>", "-e", "CONSUL_HTTP_TOKEN=<Consul HTTP Token>", "hashicorp/consul-mcp-server" ] }, "vault-mcp-server": { "command": "docker", "args": [ "run", "--rm", "-i", "-e", "VAULT_ADDR=<Vault Address>", "-e", "VAULT_TOKEN=<Vault Token>", "-e", "VAULT_NAMESPACE=<Vault Namespace>", "hashicorp/vault-mcp-server" ] }, "vault-radar-mcp-server": { "command": "docker", "args": [ "run", "--rm", "-i", "-e", "HCP_PROJECT_ID=<HCP Project ID>", "-e", "HCP_CLIENT_ID=<HCP Service Principal Client ID>", "-e", "HCP_CLIENT_SECRET=<HCP Service Principal Client Secret>", "hashicorp/vault-radar-mcp-server" ] }, "remote-pa-mcp-server-by-apiKeyBasic": { "type": "streamable-http", "url": "https://<PA_HOST>/api/<TENANT_ID>/v0/agentic-ai/ibm-pa-tools/mcp", "headers": { "Authorization": "Basic <mybase64ecoded(apikey:myapikeyvalue)>" } } } }

Related Skills

View on GitHub
GitHub Stars0
CategoryDevelopment
UpdatedNaNy ago
Forks0

Trust signals

68/100

From repository metadata: license, adoption, age and documentation. Not a code audit — see the Safety scan above for what the skill file itself contains.

2 medium1 low
mcp — MCP Server: Install & Safety Check | SkillAgent