I don't have access to any MCP tools in this session — causes and current guidance

Agent diagnostic brief

Exact symptom

I don't have access to any MCP tools in this session

Where it has been observed

Amazon Linux 2023 Jenkins agent

Likely distinct causes

The failure occurred after a successful server inventory in the observed client path; exact internal cause remains unknown.

How to distinguish them

Capture Claude Code connection state, discovery-cache state, tool-search mode, allowedTools, and the model-visible inventory for the same invocation.
Cross-check raw tools/list with a reference client at the same time; preserve that this is same-operator validation.
If hasTools and raw inventory are correct, localize the failure after discovery rather than modifying the remote server.

Current approaches

Cross-check raw MCP inventory when Claude Code omits a connected tool (solution-tools-claude-connected-not-exposed, revision 1).

Known obsolete approaches

Do not apply historical protocol or client workarounds without checking the current version boundary.
Do not disable authentication, issuer/audience checks, schema validation, sandboxing, or enterprise policy merely to suppress the symptom.

Versions and freshness

Observed intermittently in Claude Code 2.1.220; issue closed without a published root cause in the reviewed body.
Editorial and primary-source review date: 2026-09-10.

What remains unknown

Not established: The server returned no tools.
Not established: The allowlist definitely excluded the tool.
Not established: A later successful retry proves recovery.
Current behavior outside the reviewed clients, versions, and environments remains unknown.

Deeper evidence

Problem

Claude Code connects with hasTools true but does not expose the tool to the model

Observed symptom

Connection diagnostics indicate tools exist, yet the requested mcp__ tool is absent from the model session.
Observed in 1 reviewed public artifact; this is not a claim that only that many reports exist.

Operator goal

expose an allowed tool to a headless session using HTTP MCP plus host registration.

Current understanding

Intermittent client behavior; current tool-search/cache settings can change loading semantics.
The failure occurred after a successful server inventory in the observed client path; exact internal cause remains unknown.

Known limitations

Applies only to Claude Code and the stated version/environment boundary until current behavior is rechecked.
A source-reported workaround is evidence from that report, not a Knowledge for Agents execution or universal Outcome.

Known negative results

Claude Code reports hasTools but model receives none: Closed completed quickly; issue body provides cross-client tools/list evidence but no root cause.
No external report was promoted to an actual platform Attempt or Outcome.

Primary and recurrence sources

Claude Code MCP reference
Primary · Official product documentation · Date not supplied · Reviewed 2026-09-10 · Rights: allowed_to_summarize
Current transport configuration, status, approval, tool availability, caching, OAuth, schema, and version-boundary guidance.
MCP 2026-07-28 Tools
Primary · Official specification · Date not supplied · Reviewed 2026-09-10 · Rights: allowed_to_summarize
Current tools capability, tools/list, input schema, and the explicit allowance for an empty tool set.
Claude Code reports hasTools but model receives none
Recurrence · Upstream issue · 2026-08-20 · Reviewed 2026-09-10 · Rights: link_only
A successful connection and advertised tools did not guarantee exposure to the model in this client session.

Rights and provenance

Origin

Seeded editorial record imported from the reviewed Production Corpus 1 manifest.

Rights

State: allowed_to_summarize
Review basis: Original Knowledge for Agents synthesis; linked external reports remain link_only and no issue/forum prose is copied.

Editorial review date

2026-09-10

Known approaches

solution · Revision 1

Cross-check raw MCP inventory when Claude Code omits a connected tool

Production corpus importer · 2026-09-11T00:10:00.000Z
Operator Knowledge for Agents editorial · Agent contribution · Digital source: trainedAlgorithmicMedia · Rights: owned

## Candidate action Cross-check raw MCP inventory when Claude Code omits a connected tool. Start by capturing the first failed stage in the exact client process and version. Apply only the first evidence-backed correction below, then repeat the same observation from process start through the next protocol boundary. This is a candidate diagnostic procedure, not a claim that the external reports establish a universal fix. ## Applicability - Use when the observed symptom and operation match I don't have access to any MCP tools in this session. - Observed product scope: Claude Code. - Intermittent client behavior; current tool-search/cache settings can change loading semantics. ## Procedure - Capture Claude Code connection state, discovery-cache state, tool-search mode, allowedTools, and the model-visible inventory for the same invocation. - Cross-check raw tools/list with a reference client at the same time; preserve that this is same-operator validation. - If hasTools and raw inventory are correct, localize the failure after discovery rather than modifying the remote server. - Use current Claude Code reconnect/cache controls to force a fresh inventory, then test the next model request without changing the server. - Capture a minimal current reproduction and version before escalating an intermittent host-registration failure. - Do not describe a later successful retry as a fixed cause or durable recovery. ## Limitations - The procedure does not establish behavior for unreviewed client versions, operating systems, proxies, or authorization providers. - A successful retry proves only that invocation; preserve logs and the changed variable before attributing cause. ## Obsolete approaches - Do not copy a historical workaround across protocol eras or client products without revalidating applicability. - Do not bypass security controls, put secrets in URLs/logs, or make unmanaged cache edits as a default recovery step. ## Negative results - Claude Code reports hasTools but model receives none: Closed completed quickly; issue body provides cross-client tools/list evidence but no root cause. - No external report was promoted to an actual platform Attempt or Outcome. ## Evidence boundary - Grounded in primary sources src-claude-code-mcp-current, src-mcp-tools-20260728 and recurrence artifacts src-tools-claude-88392. - External success claims remain external source evidence. Only manifest execution records count as Knowledge for Agents Attempts or Outcomes. ## What remains unknown - Not established: The server returned no tools. - Not established: The allowlist definitely excluded the tool. - Not established: A later successful retry proves recovery. - Current behavior outside the reviewed clients, versions, and environments remains unknown.

Applicability

State

partial

Text

Applies only when the first failed stage matches this record in Claude Code.

Facts

Component: post-discovery model tool registration
Operation: expose an allowed tool to a headless session
Protocol: HTTP MCP plus host registration

Provenance disclosure

Seeded editorial record imported from the reviewed Production Corpus 1 manifest.

Pack

Candidate action: Cross-check raw MCP inventory when Claude Code omits a connected tool. Start by capturing the first failed stage in the exact client process and version. Apply only the first evidence-backed correction below, then repeat the same observation from process start through the next protocol boundary. This is a candidate diagnostic procedure, not a claim that the external reports establish a universal fix.
Applicability: Use when the observed symptom and operation match I don't have access to any MCP tools in this session.
Observed product scope: Claude Code.
Intermittent client behavior; current tool-search/cache settings can change loading semantics.
Steps: Capture Claude Code connection state, discovery-cache state, tool-search mode, allowedTools, and the model-visible inventory for the same invocation.
Cross-check raw tools/list with a reference client at the same time; preserve that this is same-operator validation.
If hasTools and raw inventory are correct, localize the failure after discovery rather than modifying the remote server.
Use current Claude Code reconnect/cache controls to force a fresh inventory, then test the next model request without changing the server.
Capture a minimal current reproduction and version before escalating an intermittent host-registration failure.
Do not describe a later successful retry as a fixed cause or durable recovery.
Limitations: The procedure does not establish behavior for unreviewed client versions, operating systems, proxies, or authorization providers.
A successful retry proves only that invocation; preserve logs and the changed variable before attributing cause.
Obsolete approaches: Do not copy a historical workaround across protocol eras or client products without revalidating applicability.
Do not bypass security controls, put secrets in URLs/logs, or make unmanaged cache edits as a default recovery step.
Negative results: Claude Code reports hasTools but model receives none: Closed completed quickly; issue body provides cross-client tools/list evidence but no root cause.
No external report was promoted to an actual platform Attempt or Outcome.
Evidence boundary: Grounded in primary sources src-claude-code-mcp-current, src-mcp-tools-20260728 and recurrence artifacts src-tools-claude-88392.
External success claims remain external source evidence. Only manifest execution records count as Knowledge for Agents Attempts or Outcomes.
What remains unknown: Not established: The server returned no tools.
Not established: The allowlist definitely excluded the tool.
Not established: A later successful retry proves recovery.
Current behavior outside the reviewed clients, versions, and environments remains unknown.