toolshed-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| GITHUB_TOKEN | No | GitHub token read from the environment and redacted from every error message before it can reach a log or a tool result. | |
| TOOLSHED_HOME | No | Where the cache and the source registry live. | ~/.toolshed |
| TOOLSHED_SOURCES | No | JSON array of extra source definitions. | |
| TOOLSHED_ECC_ROOT | No | Root of the ECC corpus. | |
| TOOLSHED_SNA_ROOT | No | Root of the skills-and-agents corpus. | |
| TOOLSHED_CACHE_ROOT | No | Where fetched repositories are cached. | |
| TOOLSHED_EXACT_ROOT | No | Root of the expo/exact corpus. | |
| TOOLSHED_PROXY_CONFIG | No | Where the proxy target list lives. | ~/.toolshed/proxies.json |
| TOOLSHED_FETCH_TIMEOUT_MS | No | How long a repository fetch may take. | 600000 |
| TOOLSHED_MAX_DOWNLOAD_BYTES | No | The largest archive the fallback route will download. | 52428800 |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| search_registryA | Search skills, agents and commands across every corpus registered on this machine. Returns ranked hits with the source each came from. Not covered by search_library, which searches one corpus only. |
| get_entryA | Read one skill, agent or command by id or name, including its frontmatter and body. The id is |
| get_entry_bundleA | Read one entry together with the files that belong to it, such as reference documents or scripts. Not covered by get_entry, which returns only the entry itself. |
| list_sourcesA | List every corpus registered on this machine with its kind, root and entry count. Counts are read at the time of the call. Not covered by list_mcp_servers, which lists MCP servers rather than corpora. |
| list_mcp_serversA | List MCP servers registered in the harness configs on this machine, distinguishing those whose executable is present from those that are configured only. Not covered by list_sources, which lists corpora of skills and agents. |
| list_agent_typesA | Report which agent types each harness on this machine can actually spawn, and name any built-in types that are missing. Not covered by list_mcp_servers, which lists server registrations rather than agent types. |
| add_github_sourceA | Fetch a GitHub repository, index its skills and agents, and register it as a registry source so its entries become searchable. Not covered by install_skill_from_github, which installs a single skill into a harness. |
| install_skill_from_githubA | Fetch one skill from a GitHub repository and install it into a coding harness, with the install performed by the skills-library server so its path and tier policy applies. Not covered by add_github_source, which registers a whole repository as a source. |
| proxy_callA | Invoke a tool on an external MCP server that this server proxies, addressed as server__tool. Not covered by proxy_discover, which lists the tools without calling them. |
| proxy_discoverA | List the tools exposed by an external MCP server that this server proxies, or list the proxied servers themselves when no server is named. Not covered by proxy_call, which invokes a tool rather than listing them. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 10 tools
Each tool targets a distinct action and resource, and the descriptions explicitly contrast overlapping neighbors such as get_entry vs get_entry_bundle, list_sources vs list_mcp_servers, and proxy_call vs proxy_discover. The install_skill_from_github vs add_github_source distinction is also clearly drawn.
All names use snake_case and are readable, but the pattern is not uniformly verb_noun: proxy_call and proxy_discover use a proxy_ prefix while others start with verbs like get, list, search, add, and install. Minor deviation only, not confusing.
Ten tools is well scoped for a toolshed server covering registry search, source management, harness introspection, skill installation, and MCP proxying. Each tool appears to earn its place without obvious redundancy.
The surface covers search, read, source addition, skill installation, harness listing, and proxy discovery/calls, but notable lifecycle gaps remain: no remove/uninstall/refresh operations and no single-corpus search even though search_library is referenced as a contrasting tool. These omissions could cause dead ends for agents following the descriptions.