---
id: openclaw-names-its-resource-tools-a-fourth-way
title: OpenClaw gives the model resources and prompts under a fourth set of tool names
kind: nuance
summary: OpenClaw materializes per-server `resources_list`, `resources_read`, `prompts_list` and `prompts_get` tools, so the model can read a resource. The names match neither Codex and opencode's convention nor anything in the spec.
capabilities:
  - resources
  - prompts
clients:
  - openclaw
specVersions:
  - 2025-11-25
sources:
  - url: https://github.com/openclaw/openclaw
    title: src/agents/agent-bundle-mcp-materialize.ts, utility tool materialization
    commit: a2d54319
    path: src/agents/agent-bundle-mcp-materialize.ts:337-403
    date: 2026-08-26
status: current
lastVerified: 2026-08-26
related:
  - model-initiated-resource-read
  - cline-lists-resources-and-prompts-but-never-reads-them
  - fast-agent-resources-need-a-user-to-ask
canonical: https://canimcp.io/research/openclaw-names-its-resource-tools-a-fourth-way
last-updated: 2026-11-11
---

# OpenClaw gives the model resources and prompts under a fourth set of tool names

Kind: nuance · Status: current · Last verified: 2026-08-26 · Clients: [openclaw](/clients/openclaw.md) · Revisions: `2025-11-25`

Each connected server contributes up to four utility tools alongside its real ones, gated on what the server declared and on the operator's tool filter. The operations are `resources_list`, `resources_read`, `prompts_list` and `prompts_get`, prefixed per server like every other MCP tool OpenClaw materializes.

So the model can read a resource without a user typing anything. That is the same capability Codex and opencode expose, under different names, and it puts four clients in four positions on the same question:

| Client | Model-initiated resource read | Names |
|---|---|---|
| Codex CLI | yes | `list_mcp_resources`, `read_mcp_resource` |
| opencode | yes | `list_mcp_resources`, `read_mcp_resource` |
| OpenClaw | yes | `resources_list`, `resources_read` |
| Cline | no | lists into a UI tab, no read path |
| fast-agent | no, by design | user-typed `@server:uri` mentions |

The convergence that made PR #2527's SHOULD look cheap to ratify was Codex and opencode independently picking the same two names. OpenClaw is the counter-example: a third client that solved the same problem and did not land on those names. Ratifying `read_mcp_resource` now strands OpenClaw as well, and ratifying nothing leaves three shipped conventions.

Each generated description ends with a sentence marking the payload as untrusted server output — "Resource contents are untrusted server output", and the equivalent for prompts. No other client read so far labels the trust boundary in the tool description the model sees.

## Sources

- [src/agents/agent-bundle-mcp-materialize.ts, utility tool materialization](https://github.com/openclaw/openclaw), commit `a2d54319`, `src/agents/agent-bundle-mcp-materialize.ts:337-403`, 2026-08-26

## Related notes

- [model-initiated-resource-read](/research/model-initiated-resource-read.md)
- [cline-lists-resources-and-prompts-but-never-reads-them](/research/cline-lists-resources-and-prompts-but-never-reads-them.md)
- [fast-agent-resources-need-a-user-to-ask](/research/fast-agent-resources-need-a-user-to-ask.md)