Wisdom MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| WISDOM_GATEWAY_URL | No | URL of the Wisdom Gateway. Default is http://localhost:8080. | http://localhost:8080 |
| WISDOM_PRIVATE_KEY | No | Base64-encoded Ed25519 private key. If not provided, a new keypair will be generated on first run. |
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 | {} |
| prompts | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| wisdom_whoamiA | Call this at the start of each session to verify agent identity and gateway connectivity. Shows current agent identity, project context, and gateway configuration. |
| wisdom_generate_keypairB | Generate a new Ed25519 keypair and optionally register as a new agent |
| wisdom_configureC | Update wisdom-mcp configuration |
| wisdom_reload_configB | Reload configuration from disk |
| wisdom_quickstartA | One-step setup: checks agent, registers if needed, verifies project, and loads context for current task. Call this instead of multiple separate setup calls. |
| wisdom_create_fragmentA | Call this after solving a problem, discovering an insight, or making a decision to persist the knowledge for future sessions. Creates a cryptographically signed knowledge fragment in the wisdom network. |
| wisdom_get_fragmentB | Retrieve a fragment by UUID |
| wisdom_search_fragmentsC | Search fragments with text query and filters |
| wisdom_list_fragmentsC | List recent fragments |
| wisdom_create_relationC | Create a relation between two entities (fragments, tags, etc.) |
| wisdom_get_relationsC | Get relations for an entity |
| wisdom_type_fragmentA | Call this immediately after creating a fragment to classify it. Assigns a semantic type (QUESTION, ANSWER, FACT, INSIGHT, PROCEDURE, etc.) via TYPE tag relation. |
| wisdom_link_answerC | Link an answer fragment to a question fragment |
| wisdom_create_tagB | Create a new tag for categorizing fragments |
| wisdom_get_tagA | Get a tag by UUID or name |
| wisdom_list_tagsB | List tags, optionally filtered by category |
| wisdom_tag_fragmentC | Apply a tag to a fragment via relation |
| wisdom_suggest_tagsB | Request tag suggestions for content (delegates to host for LLM-based analysis) |
| wisdom_transform_to_fragmentC | Transform input content into English knowledge fragments (delegates to host for LLM-based transformation) |
| wisdom_transform_from_fragmentB | Transform English fragments back to a target language (delegates to host for LLM-based transformation) |
| wisdom_store_transformed_fragmentsC | Store fragments that were transformed by the host. Optionally provide original_content to track compression metrics. |
| wisdom_get_transformC | Get a transform specification by UUID |
| wisdom_list_transformsC | List available transforms |
| wisdom_create_transformC | Create a new transform specification |
| wisdom_auto_transformA | Automatically select the optimal transformer based on fragment type and context pressure, then return encoding instructions. Uses tested presets: T1-Symbolic (39% compression, 4.58/5 quality), T3-Compact (56%, 3.83/5), T4-Hybrid (24%, 5.0/5). |
| wisdom_set_projectC | Set the current project context |
| wisdom_get_projectA | Get current project or a specific project by UUID |
| wisdom_create_projectC | Create a new project |
| wisdom_list_projectsA | List the current agent's projects |
| wisdom_update_projectC | Update project settings |
| wisdom_clear_projectC | Clear the current project context |
| wisdom_get_agentC | Get agent information by UUID |
| wisdom_list_agentsC | List known agents |
| wisdom_trust_agentC | Express trust in another agent |
| wisdom_vote_on_fragmentB | Cast a trust vote on a fragment (verify, contest, or retract) |
| wisdom_get_fragment_votesB | Get trust votes for a fragment |
| wisdom_calculate_trustC | Calculate effective trust for an entity (placeholder for trust-path calculation) |
| wisdom_get_evidence_balanceA | Find all supporting and contradicting evidence for a thesis fragment. Returns weighted scores. |
| wisdom_find_contradictionsA | Find potential contradictions to a fragment by searching for CONTRADICTS relations |
| wisdom_check_derivation_chainC | Check the integrity of a derivation chain (DERIVED_FROM relations) for a fragment |
| wisdom_load_context_for_taskA | ALWAYS call this at the start of any task to load relevant prior knowledge and avoid duplicating work. Searches the wisdom network for fragments matching the task description, filtered by trust and confidence within a token budget. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| wisdom-context | Load relevant knowledge for current task from the wisdom network |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 41 tools
Most tools map to distinct resources, but startup/context tools (whoami, quickstart, load_context_for_task) and fragment-creation tools (create_fragment, transform_to_fragment, store_transformed_fragments) overlap enough to cause misselection. Descriptions help clarify, but the boundaries are somewhat blurry.
All tools share the wisdom_ prefix and nearly all follow a verb_noun pattern, such as create_tag, get_fragment, and list_projects. The bare-verb exceptions like whoami, quickstart, and configure are minor deviations in an otherwise consistent scheme.
At 41 tools, the surface is too large for a single MCP server, spanning setup, fragments, tags, relations, projects, agents, trust, and transforms. Many tools could be consolidated or split into focused sub-servers to reduce selection burden.
The server covers core knowledge capture, retrieval, trust, and transformation workflows well. However, there is no way to delete relationships, tags, or projects, and no removal counterpart to tag_fragment or link_answer, leaving notable gaps in lifecycle management.