Skip to main content
Glama
mcp-trustlayer
by neelbarm

mcp-trustlayer

An MCP server that lets an agent ask whether it is allowed to act on its own output.

Python MCP Tests Dependencies License


An agent that has just extracted values from a document is the worst possible judge of whether those values are correct. It has no distance from its own output. This server moves that judgment outside the model: the agent proposes, a policy you control disposes.

agent  ──  "I extracted these 12 fields, may I write them?"  ──▶  mcp-trustlayer
                                                                       │
       ◀──  "9 post. 3 to a human. Here is why for each."  ────────────┘

Why this exists

Most extraction pipelines gate on one signal, a confidence score, and inherit a failure they never see. Confidence catches the model being unsure. It cannot catch the model being sure and wrong, because nothing in a confidently wrong answer looks hesitant.

The worked example below carries a fee field at 0.94 confidence whose value is the plan-review line item rather than the total. No threshold you could reasonably set catches it. An independent verification pass does.

Related MCP server: mcp-sequentialthinking-qa

Tools

evaluate_fields

Returns a disposition per field, one of post, review, or escaped.

{
  "fields": [
    { "name": "permit_number", "value": "BLD-2024-041877", "confidence": 0.99, "verification": "verified" },
    { "name": "permit_fee",    "value": "$1,240.00",       "confidence": 0.94, "verification": "mismatch" },
    { "name": "contractor",    "value": "Meridian",        "confidence": 0.38, "verification": "not_found" }
  ],
  "high_stakes": ["permit_number"],
  "verified": true
}
1 posted, 2 held for review, 0 escaped

[POST]    permit_number = 'BLD-2024-041877' (0.99/0.95) verified
[HOLD]    permit_fee    = '$1,240.00'       (0.94/0.85) verification mismatch
[HOLD]    contractor    = 'Meridian'        (0.38/0.85) confidence 0.38 below bar 0.85

Pass "verified": false to model what happens with no verification pass. The fee field flips to escaped, meaning it was written to the record while unsupported by its source. That number is what the second pass is worth.

calibrate_threshold

Sweeps the bar and reports review load against escaped errors, with and without verification, so the threshold gets chosen deliberately rather than inherited.

bar    verify-on: hold/escaped   verify-off: hold/escaped
0.85      3 / 0                     2 / 1
0.90      5 / 0                     4 / 1
0.95      7 / 0                     7 / 0

Install

No dependencies. Python 3.10+.

git clone https://github.com/neelbarm/mcp-trustlayer
cd mcp-trustlayer
python -m mcp_trustlayer.server

Claude Desktop

{
  "mcpServers": {
    "trustlayer": {
      "command": "python",
      "args": ["-m", "mcp_trustlayer.server"],
      "cwd": "/path/to/mcp-trustlayer"
    }
  }
}

Speaking to it directly

MCP is JSON-RPC 2.0 over stdio, so you can drive it with a pipe.

printf '%s\n' \
  '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{}}' \
  '{"jsonrpc":"2.0","id":2,"method":"tools/list","params":{}}' \
  | python -m mcp_trustlayer.server

Design notes

The protocol is implemented directly, not via an SDK. protocol.py is about 90 lines and handles initialize, tools/list, and tools/call over newline-delimited JSON-RPC. Keeping it dependency-free makes the wire format legible, which matters more in a reference implementation than convenience does.

Notifications get no response. notifications/initialized carries no id and must not be replied to. This is the most common place a hand-rolled MCP server breaks, so there is a test for it.

Tool errors return content, not crashes. A raised exception comes back as isError: true with the message in the content block, so the model can see what went wrong and adjust rather than losing the connection.

Descriptions are written for the model, not for a human reading docs. Each tool description says when to call it, because that text is the only instruction the model gets.

Tests

python -m pytest tests -q     # 10 passed

The suite includes an end-to-end case that spawns the server as a subprocess and speaks real JSON-RPC over stdio, rather than only calling the handler in-process.

MIT. Built by Neel Barmecha.

Available Tools

2 tools
calibrate_thresholdB

Sweep the confidence threshold across a range and report how review load trades against errors that get through. Use this to choose a bar deliberately rather than accepting a default.

Inputs: fields (required), low, high, step, +1 more.

evaluate_fieldsA

Decide which extracted fields may be written to a system of record and which must go to a person. Returns a disposition per field: post, review, or escaped. Call this before acting on extracted data.

Inputs: fields (required), verified, high_stakes, standard_bar, +1 more.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A3.8/5.0

    Scored across 2 tools

    Disambiguation5/5

    The two tools have clearly distinct purposes: evaluate_fields determines field dispositions, while calibrate_threshold analyzes trade-offs across threshold values. There is no overlap in their responsibilities.

    Naming Consistency5/5

    Both tools follow the same verb_noun pattern ('evaluate_fields', 'calibrate_threshold'), using consistent lowercase with underscores. The pattern is predictable and clear.

    Tool Count4/5

    With only 2 tools, the set is slightly thin, but this matches the narrow, focused scope of the trust-layer functionality. Each tool earns its place.

    Completeness3/5

    The workflow is missing a way to actually apply the calibrated threshold to the evaluate_fields tool; calibration is informational but there is no explicit 'set_threshold' or parameter. This creates a notable gap for end-to-end usage.

    Related MCP Connectors

    Related MCP Servers