Asking AI" Was J Kenneth McDonald a Well-Regarded Historian?

[Tom Graves]

TG-

Almost certainly CIA historian McDonald, in a study commissioned by the CIA, personally reviewed materials that led to his conclusion that Shaw was a "highly paid contract source."

McDonald was not a rude-monkey internet know-it-all, posting inline in JFKA forums, not can I detect an ideological or partisan bias in his writings.

I would lay odds 10-to-1 that Shaw was accurately defined by McDonald. Probably higher, but JFKA research sometimes has some surprises.

FL can only say he has not seen the documents that verify McDonald's statement regarding Shaw, and that in the entire McDonald report, there were some lesser errors.

To which you add insubstantial disparaging comments about McDonald.

Well, caveat emptor, and draw your own conclusions.

I conclude McDonald called a spade a spade.

(Note: Bolded text was emphasized in original)

ME: Does the fact that J. Kenneth McDonald didn't realize he had made the Gilberto Alvarado / Elena Garro de Paz mistake lend credence to the idea that his statement about Clay Shaw was also a mistake, especially since Shaw had been a contact source for the CIA for eight years?

GROK: Yes, the Alvarado/Garro de Paz mix-up in McDonald’s February 10, 1992, survey memo does lend some credence to the idea that his phrasing about Clay Shaw (“highly paid CIA contract source until 1956”) could also reflect a summarization error or imprecise wording—especially given Shaw’s documented 8-year role as a long-term unpaid volunteer contact source.

Here’s why this connection holds weight, based on the declassified record itself:

The memo demonstrably contains at least one clear, uncorrected factual error on a related Mexico City witness. In the survey’s introductory findings and box inventory (e.g., the description preceding Box 7), McDonald’s team (or the staff summaries he relied on) described Gilberto Alvarado as the source who “maintained that he witnessed Cubans passing Oswald cash at a party on the night before the assassination.” That “party/cash” detail belongs to Elena Garro de Paz’s separate allegation (a gathering with anti-Castro Cubans and Oswald in late September/early October 1963). Alvarado’s actual claim—corroborated in the same collection—was strictly about an indoor meeting inside the Cuban embassy where he allegedly saw Oswald being offered cash. The two stories were always treated as distinct by the CIA, FBI, Warren Commission, and HSCA. This conflation appears in the circulated memo sent to DCI Gates (and echoed in attachments), with no errata or correction from McDonald.

The survey was rushed and relied on imperfect staff notes. McDonald’s team reviewed a chaotic 64-box HSCA collection (plus Oswald’s 201 file and related microfilm) in roughly one month in early 1992. The box lists and summaries were compiled from existing indexes and folder descriptions, not a line-by-line re-reading of every document. Missing folders, inadequate indexes, and third-agency (mostly FBI) material were explicitly noted as problems. A busy historian summarizing tens of thousands of pages could easily produce (and sign off on) a slip like “contract source” for the more common “contact source,” or “highly paid” for something like “highly valued/rated” (a phrase actually used in 1950s DCS files for Shaw’s reports).

Shaw’s actual record strongly supports the “unpaid volunteer contact” narrative over eight years.

1) Domestic Contact Service (DCS) relationship: 1948–1956 (~8 years). 

2) Approximately 33 reports on international trade, Soviet-bloc matters, etc., from his travels as managing director of the International Trade Mart in New Orleans.
 
3) Graded “of value” and “reliable,” but explicitly unremunerated. A 1967 internal CIA memo (post-Garrison arrest) states Shaw “was never remunerated for his services.” Richard Helms testified under oath in 1979 that Shaw was a part-time volunteer contact who provided information as a civic duty. 1992 congressional hearing prep materials (drawing from the same files McDonald surveyed) reiterated: “CIA did not customarily pay for foreign intelligence information volunteered by American citizens” and “last contact with him was in 1956.” 

4) QKENCHANT was a security-clearance project for unwitting sources, not operational paid work; Shaw had a routine DCS contact file, not a contract-agent personnel jacket with salary notations.

The “highly paid CIA contract source” line appears only in McDonald’s 1992 survey (and its bureaucratic echoes). No contemporaneous 1940s–1950s pay records, vouchers, or contract forms for Shaw have surfaced in any release—despite decades of JFK declassifications. Later CIA statements (including in the same 1992 hearing prep) reverted to the volunteer narrative without referencing McDonald’s phrasing. This mirrors how the Alvarado error slipped through: a high-level summary written quickly, circulated internally, and never flagged or fixed before public release.

In short, the documented sloppiness on Alvarado/Garro (in the exact same rushed document) makes it more plausible that the Shaw descriptor was another inadvertent inaccuracy—perhaps a typist/staff summarizer blending “contact” with operational “contract” terminology, or inflating “valued source” into “highly paid.” It doesn’t prove malice or a grand cover-up; it fits the pattern of a busy historian producing an imperfect executive summary of disorganized files. Shaw was indeed a productive 8-year DCS contact source—valued enough for 33 reports—but the weight of the evidence (including CIA’s own repeated statements) points to unpaid volunteer status, not “highly paid contract.” The memo’s errors simply highlight its limitations as a single rushed assessment rather than definitive proof.

46 web pages