RealityFirst MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
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": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| classify_claimC | Classify an agent claim and return the evidence gate it must satisfy. |
| build_verification_planC | Build a minimal Reality-first verification plan without executing external tools. |
| check_completion_evidenceC | Check whether a completion/current-state claim has enough independent evidence. |
| validate_evidenceC | Validate evidence payload structure before it can satisfy a completion gate. |
| resolve_precedenceC | Resolve conflicting claims using Reality > CURRENT law > cutover > implementation/tests > history. |
| check_replay_safetyC | Block blind replay when side effects or request lineage are unresolved. |
| compact_evidenceC | Compact evidence while retaining source refs and prioritizing direct Reality proof. |
| record_lossB | Create a structured loss-ledger entry. This tool does not persist it. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| reality_first | Base behavior prompt for Reality-first agent work. |
| read_wide | Repository-wide coverage prompt that avoids dumping the whole repo into context. |
| crosscheck_completion | Prompt for independently verifying an agent's completion claim. |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| core_policy | Core Reality-first invariants as JSON. |
| completion_policy | Completion claim gates as JSON. |
| precedence_policy | Current-state source precedence as JSON. |
TDQS
Scored across 8 tools
Most tools have clearly distinct purposes (classify vs resolve vs compact). However, validate_evidence, check_completion_evidence, and check_replay_safety all perform gate-style checks on evidence, which could cause confusion without careful reading of descriptions.
All tool names follow a consistent snake_case verb_noun pattern (validate_evidence, resolve_precedence, check_replay_safety, etc.). There are no mixed conventions or vague verbs.
With 8 tools, the set is well-scoped for a verification/evidence-gate server. Each tool addresses a distinct step in the workflow, and there is no excessive proliferation.
The surface covers validation, classification, conflict resolution, planning, and loss recording, but record_loss explicitly does not persist entries, leaving no way to actually store or retrieve loss data. There is also no tool to execute verification or persist evidence, creating dead ends for some workflows.