universal-research-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| UNIVERSAL_RESEARCH_ROOT | No | The project root path for the research MCP server. Used when the process is not launched from the working directory containing the research project. |
Capabilities
Features and capabilities supported by this server
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| memory_search_candidatesC | Return lexical search candidates. Fetch original evidence before concluding. |
| memory_latestC | Return latest non-reference records, ordered by recorded event time. |
| memory_fetch_evidenceC | Fetch registered evidence and verify the exact candidate hash when supplied. |
| memory_audit_ledgerC | Return read-only policy and record-integrity findings for canonical JSONL. |
| governance_get_capabilitiesA | Return the fixed governance roster and non-executing host contract. |
| governance_get_role_manifestB | Return one immutable registered role manifest and its canonical hash. |
| governance_get_role_prompt_contractB | Return the internal versioned prompt contract for one registered role. |
| governance_validate_task_packetA | Validate a proposed agent task without dispatching or approving it. |
| governance_validate_decisionB | Validate a returned decision against its exact task packet. |
| governance_evaluate_gateC | Evaluate deterministic claim gates; this never grants user approval. |
| governance_prepare_codex_dispatchB | Prepare, but do not execute, a host-owned agent dispatch. |
| governance_prepare_scope_governor_receiptC | Bind a validated passing scope decision to exact governed task hashes. |
| governance_prepare_codex_critical_batchC | Prepare the isolated fixed four-reviewer critical batch. |
| governance_capture_codex_decisionB | Validate a host decision without writing it to the canonical ledger. |
| governance_assess_planC | Assess necessity, bounded work, elapsed time, difficulty, and cost evidence. |
| governance_evaluate_operationC | Return the deterministic allow/block action for one proposed tool call. |
| governance_resolve_failure_policyC | Resolve failure handling without accepting an off/unrecorded mode. |
| governance_prepare_failure_recordC | Prepare the mandatory minimum tombstone; storage remains host-owned. |
| research_index_statusA | Report derived-index health without modifying canonical research records. |
| governance_preflight_parallel_batchA | Validate a parallel batch without starting agents, models, or network. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
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/mp-juns/universal-research-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server